Search Results for author:
Found 283 papers, 118 papers with code
Local Correlation Consistency for Knowledge Distillation
Sufficient knowledge extraction from the teacher network plays a critical role in the knowledge distillation task to improve the performance of the student network.
Offset Unlearning for Large Language Models
Despite the strong capabilities of Large Language Models (LLMs) to acquire knowledge from their training corpora, the memorization of sensitive information in the corpora such as copyrighted, harmful, and private content has led to ethical and legal concerns.
HSIDMamba: Exploring Bidirectional State-Space Models for Hyperspectral Denoising
Effectively discerning spatial-spectral dependencies in HSI denoising is crucial, but prevailing methods using convolution or transformers still face computational efficiency limitations.
Self-Improvement Programming for Temporal Knowledge Graph Question Answering
Temporal Knowledge Graph Question Answering (TKGQA) aims to answer questions with temporal intent over Temporal Knowledge Graphs (TKGs).
FraGNNet: A Deep Probabilistic Model for Mass Spectrum Prediction
The process of identifying a compound from its mass spectrum is a critical step in the analysis of complex mixtures.
Monotonic Paraphrasing Improves Generalization of Language Model Prompting
In this paper, we propose monotonic paraphrasing (MonoPara), an end-to-end decoding strategy that paraphrases given prompts or instructions into their lower perplexity counterparts based on an ensemble of a paraphrase LM for prompt (or instruction) rewriting, and a target LM (i. e. the prompt or instruction executor) that constrains the generation for lower perplexity.
LocalMamba: Visual State Space Model with Windowed Selective Scan
This paper posits that the key to enhancing Vision Mamba (ViM) lies in optimizing scan directions for sequence modeling.
Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture
To this end, we present FD4MM, a new paradigm of Frequency Decoupling for Motion Magnification with a Multi-level Isomorphic Architecture to capture multi-level high-frequency details and a stable low-frequency structure (motion field) in video space.
Training Small Multimodal Models to Bridge Biomedical Competency Gap: A Case Study in Radiology Imaging
Frontier models such as GPT-4V still have major competency gaps in multimodal capabilities for biomedical applications.
From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification
We investigate common constraints in NLP tasks, categorize them into three classes based on the types of their arguments, and propose a unified framework, ACT (Aligning to ConsTraints), to automatically produce supervision signals for user alignment with constraints.
A Dataset for the Validation of Truth Inference Algorithms Suitable for Online Deployment
In this paper, we introduce a substantial crowdsourcing annotation dataset collected from a real-world crowdsourcing platform.
Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing
In this paper, we propose an innovative Bit-mask Robust Contrastive knowledge Distillation (BRCD) method, specifically devised for the distillation of semantic hashing models.
Unified Uncertainty Estimation for Cognitive Diagnosis Models
Specifically, based on the idea of estimating the posterior distributions of cognitive diagnosis model parameters, we first provide a unified objective function for mini-batch based optimization that can be more efficiently applied to a wide range of models and large datasets.
In Defense and Revival of Bayesian Filtering for Thermal Infrared Object Tracking
Deep learning-based methods monopolize the latest research in the field of thermal infrared (TIR) object tracking.
Vision-Language Navigation with Embodied Intelligence: A Survey
As a long-term vision in the field of artificial intelligence, the core goal of embodied intelligence is to improve the perception, understanding, and interaction capabilities of agents and the environment.
Automated Design and Optimization of Distributed Filtering Circuits via Reinforcement Learning
Designing distributed filtering circuits (DFCs) is complex and time-consuming, with the circuit performance relying heavily on the expertise and experience of electronics engineers.
MapTrack: Tracking in the Map
The prediction map determines whether an object is in a crowd, and we prioritize state estimations over observations when severe deformation of observations occurs, accomplished through the covariance adaptive Kalman filter.
Contrastive Instruction Tuning
Instruction tuning has been used as a promising approach to improve the performance of large language models (LLMs) on unseen tasks.
Rethinking Large Language Model Architectures for Sequential Recommendations
This design stems from our empirical observation that beam search decoding is ultimately unnecessary for sequential recommendations.
Privacy-Preserving Language Model Inference with Instance Obfuscation
Language Models as a Service (LMaaS) offers convenient access for developers and researchers to perform inference using pre-trained language models.
Improving Fairness of Automated Chest X-ray Diagnosis by Contrastive Learning
Our proposed AI model utilizes supervised contrastive learning to minimize bias in CXR diagnosis.
Instructional Fingerprinting of Large Language Models
The exorbitant cost of training Large language models (LLMs) from scratch makes it essential to fingerprint the models to protect intellectual property via ownership authentication and to ensure downstream users and developers comply with their license terms (e. g. restricting commercial use).
Rethinking Tabular Data Understanding with Large Language Models
Large Language Models (LLMs) have shown to be capable of various tasks, yet their capability in interpreting and reasoning over tabular data remains an underexplored area.
Ranked #1 on
Semantic Parsing
on WikiTableQuestions
Conversational Question Answering with Reformulations over Knowledge Graph
CornNet adopts a teacher-student architecture where a teacher model learns question representations using human writing reformulations, and a student model to mimic the teacher model's output via reformulations generated by LLMs.
AdapTraj: A Multi-Source Domain Generalization Framework for Multi-Agent Trajectory Prediction
However, the development of multi-source domain generalization in this task presents two notable issues: (1) negative transfer; (2) inadequate modeling for external factors.
Not All Steps are Equal: Efficient Generation with Progressive Diffusion Models
In the initial stage, a base denoising model is trained to encompass all timesteps.
Dynamic Frequency Domain Graph Convolutional Network for Traffic Forecasting
Complex spatial dependencies in transportation networks make traffic prediction extremely challenging.
iComMa: Inverting 3D Gaussian Splatting for Camera Pose Estimation via Comparing and Matching
We present a method named iComMa to address the 6D camera pose estimation problem in computer vision.
EulerMormer: Robust Eulerian Motion Magnification via Dynamic Filtering within Transformer
Then, we introduce a novel dynamic filter that eliminates noise cues and preserves critical features in the motion magnification and amplification generation phases.
Leveraging Generative AI for Clinical Evidence Summarization Needs to Ensure Trustworthiness
Evidence-based medicine promises to improve the quality of healthcare by empowering medical decisions and practices with the best available evidence.
Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking
While large language models (LLMs) have demonstrated increasing power, they have also given rise to a wide range of harmful behaviors.
Deceptive Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination?
During the construction of the evidence, we purposefully replace semantic clues (entities) that may lead to the correct answer with distractor clues (evidence) that will not directly lead to the correct answer but require a chain-like reasoning process.
Towards Long-term Annotators: A Supervised Label Aggregation Baseline
These annotators could leave substantial historical annotation records on the crowdsourcing platforms, which can benefit label aggregation, but are ignored by previous works.
Dense Retrieval as Indirect Supervision for Large-space Decision Making
Many discriminative natural language understanding (NLU) tasks have large label spaces.
Local Discovery by Partitioning: Polynomial-Time Causal Discovery Around Exposure-Outcome Pairs
Causal discovery is crucial for causal inference in observational studies: it can enable the identification of valid adjustment sets (VAS) for unbiased effect estimation.
Marginal Nodes Matter: Towards Structure Fairness in Graphs
Specifically, we first analyzed multiple graphs and observed that marginal nodes in graphs have a worse performance of downstream tasks than others in graph neural networks.
Exploring the relationship between response time sequence in scale answering process and severity of insomnia: a machine learning approach
The relationship between symptom severity and response time was explored, and a machine learning model was developed to predict the presence of insomnia.
SketchBodyNet: A Sketch-Driven Multi-faceted Decoder Network for 3D Human Reconstruction
Compared with natural images, freehand sketches are much more flexible to depict various shapes, providing a high potential and valuable way for 3D human reconstruction.
Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysis
Moreover, based on the proposed BasicTS and rich heterogeneous MTS datasets, we conduct an exhaustive and reproducible performance and efficiency comparison of popular models, providing insights for researchers in selecting and designing MTS forecasting models.
DiffNAS: Bootstrapping Diffusion Models by Prompting for Better Architectures
Diffusion models have recently exhibited remarkable performance on synthetic data.
Coordination Control of Discrete Event Systems under Cyber Attacks
This paper investigates the coordination control of discrete event systems in the presence of combined sensor and actuator attacks.
Self-Augmentation Improves Zero-Shot Cross-Lingual Transfer
In this paper, we propose a simple yet effective method, SALT, to improve the zero-shot cross-lingual transfer of the multilingual pretrained language models without the help of such external data.
Towards the Identifiability and Explainability for Personalized Learner Modeling: An Inductive Paradigm
However, we notice that this paradigm leads to the inevitable non-identifiability and explainability overfitting problem, which is harmful to the quantification of learners' cognitive states and the quality of web learning services.
Ensuring User-side Fairness in Dynamic Recommender Systems
In the ever-evolving landscape of user-item interactions, continual adaptation to newly collected data is crucial for recommender systems to stay aligned with the latest user preferences.
Can Linguistic Knowledge Improve Multimodal Alignment in Vision-Language Pretraining?
The multimedia community has shown a significant interest in perceiving and representing the physical world with multimodal pretrained neural network models, and among them, the visual-language pertaining (VLP) is, currently, the most captivating topic.
Attention-Based Acoustic Feature Fusion Network for Depression Detection
To rectify this, we present the novel Attention-Based Acoustic Feature Fusion Network (ABAFnet) for depression detection.
CoNe: Contrast Your Neighbours for Supervised Image Classification
Moreover, to further boost the performance, we propose ``distributional consistency" as a more informative regularization to enable similar instances to have a similar probability distribution.
SimMatchV2: Semi-Supervised Learning with Graph Consistency
Semi-Supervised image classification is one of the most fundamental problem in computer vision, which significantly reduces the need for human labor.
DSformer: A Double Sampling Transformer for Multivariate Time Series Long-term Prediction
Multivariate time series long-term prediction, which aims to predict the change of data in a long time, can provide references for decision-making.
Unfolding Once is Enough: A Deployment-Friendly Transformer Unit for Super-Resolution
Since the high resolution of intermediate features in SISR models increases memory and computational requirements, efficient SISR transformers are more favored.
HUTFormer: Hierarchical U-Net Transformer for Long-Term Traffic Forecasting
Then, we propose a novel Hierarchical U-net TransFormer (HUTFormer) to address the issues of long-term traffic forecasting.
Bipartite Ranking Fairness through a Model Agnostic Ordering Adjustment
xOrder consistently achieves a better balance between the algorithm utility and ranking fairness on a variety of datasets with different metrics.
Watch out Venomous Snake Species: A Solution to SnakeCLEF2023
The SnakeCLEF2023 competition aims to the development of advanced algorithms for snake species identification through the analysis of images and accompanying metadata.
A scoping review on multimodal deep learning in biomedical images and texts
In this scoping review, we aim to provide a comprehensive overview of the current state of the field and identify key concepts, types of studies, and research gaps with a focus on biomedical images and texts joint learning, mainly because these two were the most commonly available data types in MDL research.
Recommender Systems in the Era of Large Language Models (LLMs)
As a result, recent studies have attempted to harness the power of LLMs to enhance recommender systems.
An empirical study of using radiology reports and images to improve ICU mortality prediction
Background: The predictive Intensive Care Unit (ICU) scoring system plays an important role in ICU management because it predicts important outcomes, especially mortality.
InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models
While diffusion models excel at generating high-quality samples, their latent variables typically lack semantic meaning and are not suitable for representation learning.
A Review on Knowledge Graphs for Healthcare: Resources, Applications, and Promises
This work aims to serve as a valuable resource for understanding the potential and opportunities of HKG in health research.
RHFedMTL: Resource-Aware Hierarchical Federated Multi-Task Learning
The rapid development of artificial intelligence (AI) over massive applications including Internet-of-things on cellular network raises the concern of technical challenges such as privacy, heterogeneity and resource efficiency.
HQDec: Self-Supervised Monocular Depth Estimation Based on a High-Quality Decoder
To this end, we propose a high-quality decoder (HQDec), with which multilevel near-lossless fine-grained information, obtained by the proposed adaptive axial-normalized position-embedded channel attention sampling module (AdaAxialNPCAS), can be adaptively incorporated into a low-resolution feature map with high-level semantics utilizing the proposed adaptive information exchange scheme.
Robust Natural Language Understanding with Residual Attention Debiasing
However, previous ensemble-based debiasing methods typically apply debiasing on top-level logits without directly addressing biased attention patterns.
Knowledge Diffusion for Distillation
To address this, we propose to denoise student features using a diffusion model trained by teacher features.
Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models
We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance.
A Causal View of Entity Bias in (Large) Language Models
Building upon this SCM, we propose causal intervention techniques to mitigate entity bias for both white-box and black-box settings.
From Shortcuts to Triggers: Backdoor Defense with Denoised PoE
Language models are often at risk of diverse backdoor attacks, especially data poisoning.
Improving Factuality of Abstractive Summarization without Sacrificing Summary Quality
However, most of the prior works on training factuality-aware models have ignored the negative effect it has on summary quality.
How Fragile is Relation Extraction under Entity Replacements?
In principle, textual context determines the ground-truth relation and the RE models should be able to correctly identify the relations reflected by the textual context.
Locate and Beamform: Two-dimensional Locating All-neural Beamformer for Multi-channel Speech Separation
Recently, stunning improvements on multi-channel speech separation have been achieved by neural beamformers when direction information is available.
Deep ReLU Networks Have Surprisingly Simple Polytopes
A ReLU network is a piecewise linear function over polytopes.
Automated Data Denoising for Recommendation
In real-world scenarios, most platforms collect both large-scale, naturally noisy implicit feedback and small-scale yet highly relevant explicit feedback.
Patchwork Learning: A Paradigm Towards Integrative Analysis across Diverse Biomedical Data Sources
By offering a more comprehensive approach to healthcare data integration, patchwork learning has the potential to revolutionize the clinical applicability of ML models.
Towards clinical AI fairness: A translational perspective
In this paper, we discuss the misalignment between technical and clinical perspectives of AI fairness, highlight the barriers to AI fairness' translation to healthcare, advocate multidisciplinary collaboration to bridge the knowledge gap, and provide possible solutions to address the clinical concerns pertaining to AI fairness.
Can GPT-4 Perform Neural Architecture Search?
We investigate the potential of GPT-4~\cite{gpt4} to perform Neural Architecture Search (NAS) -- the task of designing effective neural architectures.
Context-aware Domain Adaptation for Time Series Anomaly Detection
We formulate context sampling into the Markov decision process and exploit deep reinforcement learning to optimize the time series domain adaptation process via context sampling and design a tailored reward function to generate domain-invariant features that better align two domains for anomaly detection.
Crowd Counting with Sparse Annotation
This paper presents a new annotation method called Sparse Annotation (SA) for crowd counting, which reduces human labeling efforts by sparsely labeling individuals in an image.
Neural Multi-network Diffusion towards Social Recommendation
Graph Neural Networks (GNNs) have been widely applied on a variety of real-world applications, such as social recommendation.
FactReranker: Fact-guided Reranker for Faithful Radiology Report Summarization
We propose to extract medical facts of the input medical report, its gold summary, and candidate summaries based on the RadGraph schema and design the fact-guided reranker to efficiently incorporate the extracted medical facts for selecting the optimal summary.
FedLP: Layer-wise Pruning Mechanism for Communication-Computation Efficient Federated Learning
By adopting layer-wise pruning in local training and federated updating, we formulate an explicit FL pruning framework, FedLP (Federated Layer-wise Pruning), which is model-agnostic and universal for different types of deep learning models.
NetMoST: A network-based machine learning approach for subtyping schizophrenia using polygenic SNP allele biomarkers
Subtyping neuropsychiatric disorders like schizophrenia is essential for improving the diagnosis and treatment of complex diseases.
Evaluate underdiagnosis and overdiagnosis bias of deep learning model on primary open-angle glaucoma diagnosis in under-served patient populations
In the United States, primary open-angle glaucoma (POAG) is the leading cause of blindness, especially among African American and Hispanic individuals.
Towards NeuroAI: Introducing Neuronal Diversity into Artificial Neural Networks
In the human brain, neuronal diversity is an enabling factor for all kinds of biological intelligent behaviors.
Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All in One Classifier
The SCL loss weakens the adverse effects of the data augmentation view-noise problem which is amplified in domain transfer tasks.
Ranked #3 on
Universal Domain Adaptation
on Office-31
Medical Knowledge Graph QA for Drug-Drug Interaction Prediction based on Multi-hop Machine Reading Comprehension
Drug-drug interaction prediction is a crucial issue in molecular biology.
CbwLoss: Constrained Bidirectional Weighted Loss for Self-supervised Learning of Depth and Pose
Photometric differences are widely used as supervision signals to train neural networks for estimating depth and camera pose from unlabeled monocular videos.
Denoising Self-attentive Sequential Recommendation
Transformer-based sequential recommenders are very powerful for capturing both short-term and long-term sequential item dependencies.
MIMO-DBnet: Multi-channel Input and Multiple Outputs DOA-aware Beamforming Network for Speech Separation
Recently, many deep learning based beamformers have been proposed for multi-channel speech separation.
Improving Training and Inference of Face Recognition Models via Random Temperature Scaling
Intuitively, FR algorithms can benefit from both the estimation of uncertainty and the detection of out-of-distribution (OOD) samples.
SMARTQUERY: An Active Learning Framework for Graph Neural Networks through Hybrid Uncertainty Reduction
Graph neural networks have achieved significant success in representation learning.
SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
We present SadTalker, which generates 3D motion coefficients (head pose, expression) of the 3DMM from audio and implicitly modulates a novel 3D-aware face render for talking head generation.
Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All-in-One Classifier
The SCL loss weakens the adverse effects of the data augmentation view-noise problem which is amplified in domain transfer tasks.
Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields
Neural Radiance Fields (NeRF) have achieved photorealistic novel views synthesis; however, the requirement of accurate camera poses limits its application.
Combating Health Misinformation in Social Media: Characterization, Detection, Intervention, and Open Issues
Because of the uniqueness and importance of combating health misinformation in social media, we conduct this survey to further facilitate interdisciplinary research on this problem.
AD-BERT: Using Pre-trained contextualized embeddings to Predict the Progression from Mild Cognitive Impairment to Alzheimer's Disease
Materials and Methods: We identified 3657 patients diagnosed with MCI together with their progress notes from Northwestern Medicine Enterprise Data Warehouse (NMEDW) between 2000-2020.
Salience Allocation as Guidance for Abstractive Summarization
Recent literature adds extractive summaries as guidance for abstractive summarization models to provide hints of salient content and achieves better performance.
Ranked #7 on
Abstractive Text Summarization
on CNN / Daily Mail
Regularized Data Programming with Automated Bayesian Prior Selection
The cost of manual data labeling can be a significant obstacle in supervised learning.
Application of Deep Learning on Single-Cell RNA-sequencing Data Analysis: A Review
Single-cell RNA-sequencing (scRNA-seq) has become a routinely used technique to quantify the gene expression profile of thousands of single cells simultaneously.
Cross-Modality Domain Adaptation for Freespace Detection: A Simple yet Effective Baseline
To better bridge the domain gap between source domain (synthetic data) and target domain (real-world data), we also propose a Selective Feature Alignment (SFA) module which only aligns the features of consistent foreground area between the two domains, thus realizing inter-domain intra-modality adaptation.
A Novel Semi-supervised Meta Learning Method for Subject-transfer Brain-computer Interface
The proposed SSML learns a meta model with the existing subjects first, then fine-tunes the model in a semi-supervised learning manner, i. e. using few labeled and many unlabeled samples of target subject for calibration.
Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting
These results suggest that we can design efficient and effective models as long as they solve the indistinguishability of samples, without being limited to STGNNs.
Boosting Video Super Resolution with Patch-Based Temporal Redundancy Optimization
We develop two simple yet effective plug and play methods to improve the performance of existing local and non-local propagation-based VSR algorithms on widely-used public videos.
ScaleNet: Searching for the Model to Scale
Recently, community has paid increasing attention on model scaling and contributed to developing a model family with a wide spectrum of scales.
LightViT: Towards Light-Weight Convolution-Free Vision Transformers
Vision transformers (ViTs) are usually considered to be less light-weight than convolutional neural networks (CNNs) due to the lack of inductive bias.
Uncertainty-Aware Learning Against Label Noise on Imbalanced Datasets
The second issue refers to that models may output misleading predictions due to epistemic uncertainty and aleatoric uncertainty, thus existing methods that rely solely on the output probabilities may fail to distinguish confident samples.
HEAD: HEtero-Assists Distillation for Heterogeneous Object Detectors
We observe that the core difficulty for heterogeneous KD (hetero-KD) is the significant semantic gap between the backbone features of heterogeneous detectors due to the different optimization manners.
Geometric Matrix Completion via Sylvester Multi-Graph Neural Network
Despite the success of the Sylvester equation empowered methods on various graph mining applications, such as semi-supervised label learning and network alignment, there also exists several limitations.
Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting
However, intuitively, traffic data encompasses two different kinds of hidden time series signals, namely the diffusion signals and inherent signals.
Ranked #3 on
Traffic Prediction
on PEMS-BAY
Tree-Guided Rare Feature Selection and Logic Aggregation with Electronic Health Records Data
In a suicide risk study with EHR data, our approach is able to select and aggregate prior mental health diagnoses as guided by the diagnosis hierarchy of the International Classification of Diseases.
Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting
However, the patterns of time series and the dependencies between them (i. e., the temporal and spatial patterns) need to be analyzed based on long-term historical MTS data.
Ranked #2 on
Traffic Prediction
on PEMS-BAY
(using extra training data)
Response to: Significance and stability of deep learning-based identification of subtypes within major psychiatric disorders. Molecular Psychiatry (2022)
They questioned the generalizability of our methods and the statistical significance, stability, and overfitting of the results, and proposed a pipeline for disease subtyping.
Masked Distillation with Receptive Tokens
To obtain a group of masks, the receptive tokens are learned via the regular task loss but with teacher fixed, and we also leverage a Dice loss to enrich the diversity of learned masks.
Green Hierarchical Vision Transformer for Masked Image Modeling
We present an efficient approach for Masked Image Modeling (MIM) with hierarchical Vision Transformers (ViTs), allowing the hierarchical ViTs to discard masked patches and operate only on the visible ones.
Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing
Due to shortcuts from surface patterns to annotated entity labels and biased training, existing entity typing models are subject to the problem of spurious correlations.
Knowledge Distillation from A Stronger Teacher
In this paper, we show that simply preserving the relations between the predictions of teacher and student would suffice, and propose a correlation-based loss to capture the intrinsic inter-class relations from the teacher explicitly.
Ranked #2 on
Knowledge Distillation
on ImageNet
(using extra training data)
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning
This prunes the full self-attention structure into an order-invariant graph attention that captures the connected graph structure of cells belonging to the same row or column, and it differentiates between relevant cells and irrelevant cells from the structural perspective.
Ranked #2 on
Data-to-Text Generation
on ToTTo
A Keypoint-based Global Association Network for Lane Detection
Earlier works follow a top-down roadmap to regress predefined anchors into various shapes of lane lines, which lacks enough flexibility to fit complex shapes of lanes due to the fixed anchor shapes.
Ranked #4 on
Lane Detection
on TuSimple
(F1 score metric)
Multimodal Machine Learning in Precision Health
Attempts to improve prediction and resemble the multimodal nature of clinical expert decision-making this has been met in the computational field of machine learning by a fusion of disparate data.
BiSyn-GAT+: Bi-Syntax Aware Graph Attention Network for Aspect-based Sentiment Analysis
Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task that aims to align aspects and corresponding sentiments for aspect-specific sentiment polarity inference.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
TR-MOT: Multi-Object Tracking by Reference
RS takes previous detected results as references to aggregate the corresponding features from the combined features of the adjacent frames and makes a one-to-one track state prediction for each reference in parallel.
Learning Where to Learn in Cross-View Self-Supervised Learning
In this paper, we present a new approach, Learning Where to Learn (LEWEL), to adaptively aggregate spatial information of features, so that the projected embeddings could be exactly aligned and thus guide the feature learning better.
UV Volumes for Real-time Rendering of Editable Free-view Human Performance
Neural volume rendering enables photo-realistic renderings of a human performer in free-view, a critical task in immersive VR/AR applications.
Searching for Network Width with Bilaterally Coupled Network
In BCNet, each channel is fairly trained and responsible for the same amount of network widths, thus each network width can be evaluated more accurately.
DyRep: Bootstrapping Training with Dynamic Re-parameterization
Structural re-parameterization (Rep) methods achieve noticeable improvements on simple VGG-style networks.
Relational Self-Supervised Learning
Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations.
Ranked #60 on
Self-Supervised Image Classification
on ImageNet
SimMatch: Semi-supervised Learning with Similarity Matching
Learning with few labeled data has been a longstanding problem in the computer vision and machine learning research community.
Where Does the Performance Improvement Come From? -- A Reproducibility Concern about Image-Text Retrieval
In contrast to previous works, we focus on the reproducibility of the approaches and the examination of the elements that lead to improved performance by pretrained and nonpretrained models in retrieving images and text.
CTformer: Convolution-free Token2Token Dilated Vision Transformer for Low-dose CT Denoising
Furthermore, an overlapped inference mechanism is introduced to effectively eliminate the boundary artifacts that are common for encoder-decoder-based denoising models.
Relational Surrogate Loss Learning
Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e. g., average precision and F1 score.
Structure-Based Drug-Drug Interaction Detection via Expressive Graph Convolutional Networks and Deep Sets
In this work, we proposed a DDI detection method based on molecular structures using graph convolutional networks and deep sets.
A Privacy-Preserving Unsupervised Domain Adaptation Framework for Clinical Text Analysis
To evaluate our proposed method's utility and privacy loss, we apply our model on a medical report disease label classification task using two noisy challenging clinical text datasets.
Manifoldron: Direct Space Partition via Manifold Discovery
A neural network with the widely-used ReLU activation has been shown to partition the sample space into many convex polytopes for prediction.
Forecast-based Multi-aspect Framework for Multivariate Time-series Anomaly Detection
Today's cyber-world is vastly multivariate.
Face2Exp: Combating Data Biases for Facial Expression Recognition
To combat the mismatch between FR and FER data, Meta-Face2Exp uses a circuit feedback mechanism, which improves the base network with the feedback from the adaptation network.
You Can Wash Better: Daily Handwashing Assessment with Smartwatches
We propose UWash, an intelligent solution upon smartwatches, to assess handwashing for the purpose of raising users' awareness and cultivating habits in high-quality handwashing.
Deep Recurrent Neural Network with Multi-scale Bi-directional Propagation for Video Deblurring
Instead of estimating alignment information, we propose a simple and effective deep Recurrent Neural Network with Multi-scale Bi-directional Propagation (RNN-MBP) to effectively propagate and gather the information from unaligned neighboring frames for better video deblurring.
Ranked #12 on
Deblurring
on GoPro
Incentive Compatible Pareto Alignment for Multi-Source Large Graphs
Challenges of the problem include 1) how to align large-scale entities between sources to share information and 2) how to mitigate negative transfer from joint learning multi-source data.
GreedyNASv2: Greedier Search with a Greedy Path Filter
In this paper, we leverage an explicit path filter to capture the characteristics of paths and directly filter those weak ones, so that the search can be thus implemented on the shrunk space more greedily and efficiently.
Clinical Evidence Engine: Proof-of-Concept For A Clinical-Domain-Agnostic Decision Support Infrastructure
As a result, clinicians cannot easily or rapidly scrutinize the CDSS recommendation when facing a difficult diagnosis or treatment decision in practice.
Persona Authentication through Generative Dialogue
In this paper we define and investigate the problem of \emph{persona authentication}: learning a conversational policy to verify the consistency of persona models.
On Expressivity and Trainability of Quadratic Networks
Despite promising results so far achieved by networks of quadratic neurons, there are important issues not well addressed.
SCEHR: Supervised Contrastive Learning for Clinical Risk Prediction using Electronic Health Records
We propose a general supervised contrastive loss $\mathcal{L}_{\text{Contrastive Cross Entropy} } + \lambda \mathcal{L}_{\text{Supervised Contrastive Regularizer}}$ for learning both binary classification (e. g. in-hospital mortality prediction) and multi-label classification (e. g. phenotyping) in a unified framework.
Weakly Supervised Contrastive Learning
Specifically, our proposed framework is based on two projection heads, one of which will perform the regular instance discrimination task.
Using Subobservers to Synthesize Opacity-Enforcing Supervisors
In discrete-event system control, the worst-case time complexity for computing a system's observer is exponential in the number of that system's states.
Few-shot graph link prediction with domain adaptation
In this work, we propose an adversarial training based modification to the current state-of-the-arts link prediction method to solve this problem.
Correcting the User Feedback-Loop Bias for Recommendation Systems
We empirically validated the existence of such user feedback-loop bias in real world recommendation systems and compared the performance of our method with the baseline models that are either without de-biasing or with propensity scores estimated by other methods.
Table-based Fact Verification with Salience-aware Learning
From one perspective, our system conducts masked salient token prediction to enhance the model for alignment and reasoning between the table and the statement.
Ranked #8 on
Table-based Fact Verification
on TabFact
Heterogeneous Graph Neural Network with Multi-view Representation Learning
Graph neural networks for heterogeneous graph embedding is to project nodes into a low-dimensional space by exploring the heterogeneity and semantics of the heterogeneous graph.
Neural Network Gaussian Processes by Increasing Depth
Inspired by a width-depth symmetry consideration, we use a shortcut network to show that increasing the depth of a neural network can also give rise to a Gaussian process, which is a valuable addition to the existing theory and contributes to revealing the true picture of deep learning.
Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning
In this paper, we propose an FL framework to jointly consider performance consistency and algorithmic fairness across different local clients (data sources).
Collaboration Equilibrium in Federated Learning
Federated learning (FL) refers to the paradigm of learning models over a collaborative research network involving multiple clients without sacrificing privacy.
Event2Graph: Event-driven Bipartite Graph for Multivariate Time-series Anomaly Detection
Modeling inter-dependencies between time-series is the key to achieve high performance in anomaly detection for multivariate time-series data.
ReSSL: Relational Self-Supervised Learning with Weak Augmentation
Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations.
Ranked #78 on
Self-Supervised Image Classification
on ImageNet
ClueReader: Heterogeneous Graph Attention Network for Multi-hop Machine Reading Comprehension
Multi-hop machine reading comprehension is a challenging task in natural language processing as it requires more reasoning ability across multiple documents.
MFR 2021: Masked Face Recognition Competition
These teams successfully submitted 18 valid solutions.
ViTAS: Vision Transformer Architecture Search
Vision transformers (ViTs) inherited the success of NLP but their structures have not been sufficiently investigated and optimized for visual tasks.
Learning To Restore Hazy Video: A New Real-World Dataset and a New Method
On the other hand, the video dehazing algorithms, which can acquire more satisfying dehazing results by exploiting the temporal redundancy from neighborhood hazy frames, receive less attention due to the absence of the video dehazing datasets.
S-LIME: Stabilized-LIME for Model Explanation
An increasing number of machine learning models have been deployed in domains with high stakes such as finance and healthcare.
K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets
The operation weight for each path is represented as a convex combination of items in a dictionary with a simplex code.
BCNet: Searching for Network Width with Bilaterally Coupled Network
In BCNet, each channel is fairly trained and responsible for the same amount of network widths, thus each network width can be evaluated more accurately.
Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation
Though 3D convolutions are amenable to recognizing which actor is performing the queried actions, it also inevitably introduces misaligned spatial information from adjacent frames, which confuses features of the target frame and yields inaccurate segmentation.
Ranked #8 on
Referring Expression Segmentation
on J-HMDB
Retrieving Complex Tables with Multi-Granular Graph Representation Learning
The task of natural language table retrieval (NLTR) seeks to retrieve semantically relevant tables based on natural language queries.
Reconstructing 3D Model from Single-View Sketch with Deep Neural Network
It creates the transformation representation of a sketch by extracting the shape features of an input sketch and transformation template samples.
Research on Optimization Method of Multi-scale Fish Target Fast Detection Network
The fish target detection algorithm lacks a good quality data set, and the algorithm achieves real-time detection with lower power consumption on embedded devices, and it is difficult to balance the calculation speed and identification ability.
Prioritized Architecture Sampling with Monto-Carlo Tree Search
One-shot neural architecture search (NAS) methods significantly reduce the search cost by considering the whole search space as one network, which only needs to be trained once.
MogFace: Towards a Deeper Appreciation on Face Detection
As a result, practical solutions on label assignment, scale-level data augmentation, and reducing false alarms are necessary for advancing face detectors.
Ranked #13 on
Face Detection
on WIDER Face (Easy)
Reformulating HOI Detection as Adaptive Set Prediction
To attain this, we map a trainable interaction query set to an interaction prediction set with a transformer.
Ranked #29 on
Human-Object Interaction Detection
on HICO-DET
(using extra training data)
Mapping the phase diagram of the quantum anomalous Hall and topological Hall effects in a dual-gated magnetic topological insulator heterostructure
We use magnetotransport in dual-gated magnetic topological insulator heterostructures to map out a phase diagram of the topological Hall and quantum anomalous Hall effects as a function of the chemical potential (primarily determined by the back gate voltage) and the asymmetric potential (primarily determined by the top gate voltage).
Mesoscale and Nanoscale Physics
Locally Free Weight Sharing for Network Width Search
In this paper, to better evaluate each width, we propose a locally free weight sharing strategy (CafeNet) accordingly.
Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search
Our method enables differentiable sparsification, and keeps the derived architecture equivalent to that of Engine-cell, which further improves the consistency between search and evaluation.
Temporal boundary solitons and extreme super-thermal light statistics
We discover the formation of a temporal boundary soliton (TBS) in the close proximity of a temporal boundary, moving in a nonlinear optical medium, upon high-intensity pulse collision with the boundary.
Optics Pattern Formation and Solitons
Contrastive Learning Improves Critical Event Prediction in COVID-19 Patients
This has been a major issue for developing ML models for the coronavirus-disease 2019 (COVID-19) pandemic where data is highly imbalanced, particularly within electronic health records (EHR) research.
Adversarial Example Detection Using Latent Neighborhood Graph
We present the first graph-based adversarial detection method that constructs a Latent Neighborhood Graph (LNG) around an input example to determine if the input example is adversarial.
EnTranNAS: Towards Closing the Gap between the Architectures in Search and Evaluation
The Engine-cell is differentiable for architecture search, while the Transit-cell only transits the current sub-graph by architecture derivation.
Explicit Learning Topology for Differentiable Neural Architecture Search
Differentiable neural architecture search (NAS) has gained much success in discovering more flexible and diverse cell types.
Learning With Privileged Tasks
Concretely, we introduce a privileged parameter so that the optimization direction does not necessarily follow the gradient from the privileged tasks, but concentrates more on the target tasks.
Biomedical Knowledge Graph Refinement with Embedding and Logic Rules
This paper proposes a method BioGRER to improve the BioKG's quality, which comprehensively combines the knowledge graph embedding and logic rules that support and negate triplets in the BioKG.
SUSY Breaking Constraints on Modular flavor $S_3$ Invariant $SU(5)$ GUT Model
Modular flavor symmetry can be used to explain the quark and lepton flavor structures.
High Energy Physics - Phenomenology
Agree to Disagree: Adaptive Ensemble Knowledge Distillation in Gradient Space
In this paper, we examine the diversity of teacher models in the gradient space and regard the ensemble knowledge distillation as a multi-objective optimization problem so that we can determine a better optimization direction for the training of student network.
3D Registration for Self-Occluded Objects in Context
While much progress has been made on the task of 3D point cloud registration, there still exists no learning-based method able to estimate the 6D pose of an object observed by a 2. 5D sensor in a scene.
Stretchable Cells Help DARTS Search Better
However, even for this consistent search, the searched cells often suffer from poor performance, especially for the supernet with fewer layers, as current DARTS methods are prone to wide and shallow cells, and this topology collapse induces sub-optimal searched cells.
A Method to Generate High Precision Mesh Model and RGB-D Datasetfor 6D Pose Estimation Task
Recently, 3D version has been improved greatly due to the development of deep neural networks.
CODER: Knowledge infused cross-lingual medical term embedding for term normalization
This paper proposes CODER: contrastive learning on knowledge graphs for cross-lingual medical term representation.
Data Agnostic Filter Gating for Efficient Deep Networks
To deploy a well-trained CNN model on low-end computation edge devices, it is usually supposed to compress or prune the model under certain computation budget (e. g., FLOPs).
ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding
By doing so, our network for search at each update satisfies the sparsity constraint and is efficient to train.
Robust Finite Mixture Regression for Heterogeneous Targets
FMR is an effective scheme for handling sample heterogeneity, where a single regression model is not enough for capturing the complexities of the conditional distribution of the observed samples given the features.
Domain Agnostic Learning for Unbiased Authentication
We further extend our method to a meta-learning framework to pursue more thorough domain-difference elimination.
Deep Representation Learning of Patient Data from Electronic Health Records (EHR): A Systematic Review
We show the importance and feasibility of learning comprehensive representations of patient EHR data through a systematic review.
Survival Modeling of Suicide Risk with Rare and Uncertain Diagnoses
Motivated by the pressing need for suicide prevention through improving behavioral healthcare, we use medical claims data to study the risk of subsequent suicide attempts for patients who were hospitalized due to suicide attempts and later discharged.
A Federated Multi-View Deep Learning Framework for Privacy-Preserving Recommendations
Federated Learning(FL) is a newly developed privacy-preserving machine learning paradigm to bridge data repositories without compromising data security and privacy.
A(DP)$^2$SGD: Asynchronous Decentralized Parallel Stochastic Gradient Descent with Differential Privacy
A popular distributed learning strategy is federated learning, where there is a central server storing the global model and a set of local computing nodes updating the model parameters with their corresponding data.
Dynamic Knowledge Distillation for Black-box Hypothesis Transfer Learning
In real world applications like healthcare, it is usually difficult to build a machine learning prediction model that works universally well across different institutions.
Visualizing Deep Graph Generative Models for Drug Discovery
Drug discovery aims at designing novel molecules with specific desired properties for clinical trials.
CorefQA: Coreference Resolution as Query-based Span Prediction
In this paper, we present CorefQA, an accurate and extensible approach for the coreference resolution task.
Ranked #2 on
Coreference Resolution
on CoNLL 2012
(using extra training data)
MoFlow: An Invertible Flow Model for Generating Molecular Graphs
Generating molecular graphs with desired chemical properties driven by deep graph generative models provides a very promising way to accelerate drug discovery process.
Towards Model-Agnostic Post-Hoc Adjustment for Balancing Ranking Fairness and Algorithm Utility
Bipartite ranking, which aims to learn a scoring function that ranks positive individuals higher than negative ones from labeled data, is widely adopted in various applications where sample prioritization is needed.
Why Attentions May Not Be Interpretable?
In this paper, we demonstrate that one root cause of this phenomenon is the combinatorial shortcuts, which means that, in addition to the highlighted parts, the attention weights themselves may carry extra information that could be utilized by downstream models after attention layers.
Deep Learning Based Single Sample Per Person Face Recognition: A Survey
Face recognition under this situation is referred to as single sample face recognition and poses significant challenges to the effective training of deep models.
Adversarial Infidelity Learning for Model Interpretation
A popular way of performing model interpretation is Instance-wise Feature Selection (IFS), which provides an importance score of each feature representing the data samples to explain how the model generates the specific output.
Learning 3D-3D Correspondences for One-shot Partial-to-partial Registration
While 3D-3D registration is traditionally tacked by optimization-based methods, recent work has shown that learning-based techniques could achieve faster and more robust results.
