Search Results for author:
Found 126 papers, 52 papers with code
HILL: Hierarchy-aware Information Lossless Contrastive Learning for Hierarchical Text Classification
Existing self-supervised methods in natural language processing (NLP), especially hierarchical text classification (HTC), mainly focus on self-supervised contrastive learning, extremely relying on human-designed augmentation rules to generate contrastive samples, which can potentially corrupt or distort the original information.
TDIP: Tunable Deep Image Processing, a Real Time Melt Pool Monitoring Solution
The TDIP model is then further improved to account for MP geometries and fabrication quality based on the vision input and process parameters.
Brain-on-Switch: Towards Advanced Intelligent Network Data Plane via NN-Driven Traffic Analysis at Line-Speed
Many types of NNs (such as Recurrent Neural Network (RNN), and transformers) that are designed to work with sequential data have advantages over tree-based models, because they can take raw network data as input without complex feature computations on the fly.
A Selective Review on Statistical Methods for Massive Data Computation: Distributed Computing, Subsampling, and Minibatch Techniques
A huge amount of statistical methods for massive data computation have been rapidly developed in the past decades.
Pencil: Private and Extensible Collaborative Learning without the Non-Colluding Assumption
In this paper, we present Pencil, the first private training framework for collaborative learning that simultaneously offers data privacy, model privacy, and extensibility to multiple data providers, without relying on the non-colluding assumption.
Qubit-Wise Architecture Search Method for Variational Quantum Circuits
Considering the noise level limit, one crucial aspect for quantum machine learning is to design a high-performing variational quantum circuit architecture with small number of quantum gates.
Defending Against Data Reconstruction Attacks in Federated Learning: An Information Theory Approach
According to the channel model, we propose algorithms to constrain the information transmitted in a single round of local training.
Delving into Dark Regions for Robust Shadow Detection
Our key insight to this problem is that existing methods typically learn discriminative shadow features from the whole image globally, covering the full range of intensity values, and may not learn the subtle differences between shadow and non-shadow pixels in dark regions.
Recasting Regional Lighting for Shadow Removal
Based on this observation, we propose to condition the restoration of attenuated textures on the corrected local lighting in the shadow region.
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems
Based on this, we propose a comprehensive taxonomy, which systematically analyzes potential risks associated with each module of an LLM system and discusses the corresponding mitigation strategies.
Graph Neural Ordinary Differential Equations-based method for Collaborative Filtering
This inspired us to address the computational limitations of GCN-based models by designing a simple and efficient NODE-based model that can skip some GCN layers to reach the final state, thus avoiding the need to create many layers.
Green Beamforming Design for Integrated Sensing and Communication Systems: A Practical Approach Using Beam-Matching Error Metrics
In this paper, we propose a green beamforming design for the integrated sensing and communication (ISAC) system, using beam-matching error to assess radar performance.
Robust NOMA-assisted OTFS-ISAC Network Design with 3D Motion Prediction Topology
This paper proposes a novel non-orthogonal multiple access (NOMA)-assisted orthogonal time-frequency space (OTFS)-integrated sensing and communication (ISAC) network, which uses unmanned aerial vehicles (UAVs) as air base stations to support multiple users.
Antenna Response Consistency Driven Self-supervised Learning for WIFI-based Human Activity Recognition
We attribute this issue to the inappropriate alignment criteria, which disrupt the semantic distance consistency between the feature space and the input space.
A Geometrical Approach to Evaluate the Adversarial Robustness of Deep Neural Networks
Hence, given different inputs, it requires different time for converging to an adversarial sample.
RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models
The advent of Large Language Models (LLMs) has paved the way for complex tasks such as role-playing, which enhances user interactions by enabling models to imitate various characters.
OWL: A Large Language Model for IT Operations
However, there is a lack of specialized LLMs for IT operations.
Large Language Model for Science: A Study on P vs. NP
In this work, we use large language models (LLMs) to augment and accelerate research on the P versus NP problem, one of the most important open problems in theoretical computer science and mathematics.
Referring Image Segmentation Using Text Supervision
Hence, we propose a novel weakly-supervised RIS framework to formulate the target localization problem as a classification process to differentiate between positive and negative text expressions.
SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Device
To effectively connect the results by asymmetrical branches, a Quadratic Connection Unit(QCU) is proposed.
EQ-Net: Elastic Quantization Neural Networks
In this paper, we explore a one-shot network quantization regime, named Elastic Quantization Neural Networks (EQ-Net), which aims to train a robust weight-sharing quantization supernet.
Lighting up NeRF via Unsupervised Decomposition and Enhancement
Neural Radiance Field (NeRF) is a promising approach for synthesizing novel views, given a set of images and the corresponding camera poses of a scene.
Self-Supervised Learning for WiFi CSI-Based Human Activity Recognition: A Systematic Study
Therefore, considerable efforts have been made to address the challenge of insufficient data in deep learning by leveraging SSL algorithms.
Pulse Shape-Aided Multipath Delay Estimation for Fine-Grained WiFi Sensing
Considering the limited number of paths in physical environments, we formulate the multipath delay estimation as a sparse recovery problem.
RF-Based Simultaneous Localization and Source Seeking for Multi-Robot Systems
This paper considers a radio-frequency (RF)-based simultaneous localization and source-seeking (SLASS) problem in multi-robot systems, where multiple robots jointly localize themselves and an RF source using distance-only measurements extracted from RF signals and then control themselves to approach the source.
HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classification
Hierarchical text classification (HTC) is a challenging subtask of multi-label classification as the labels form a complex hierarchical structure.
Interactive Natural Language Processing
Interactive Natural Language Processing (iNLP) has emerged as a novel paradigm within the field of NLP, aimed at addressing limitations in existing frameworks while aligning with the ultimate goals of artificial intelligence.
SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning
In contrastive learning, the choice of ``view'' controls the information that the representation captures and influences the performance of the model.
Detecting Political Opinions in Tweets through Bipartite Graph Analysis: A Skip Aggregation Graph Convolution Approach
Public opinion is a crucial factor in shaping political decision-making.
MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning
The first Multimodal Emotion Recognition Challenge (MER 2023) was successfully held at ACM Multimedia.
Graph Collaborative Signals Denoising and Augmentation for Recommendation
Moreover, we show that the inclusion of user-user and item-item correlations can improve recommendations for users with both abundant and insufficient interactions.
Deploying Offline Reinforcement Learning with Human Feedback
To address this issue, we propose an alternative framework that involves a human supervising the RL models and providing additional feedback in the online deployment phase.
SAT Requires Exhaustive Search
In this paper, by constructing extremely hard examples of CSP (with large domains) and SAT (with long clauses), we prove that such examples cannot be solved without exhaustive search, which is stronger than P $\neq$ NP.
Multimodal Federated Learning via Contrastive Representation Ensemble
In this work, we propose Contrastive Representation Ensemble and Aggregation for Multimodal FL (CreamFL), a multimodal federated learning framework that enables training larger server models from clients with heterogeneous model architectures and data modalities, while only communicating knowledge on public dataset.
Orthogonal-Time-Frequency-Space Signal Design for Integrated Data and Energy Transfer: Benefits from Doppler Offsets
Integrated data and energy transfer (IDET) is an advanced technology for enabling energy sustainability for massively deployed low-power electronic consumption components.
MAKE: Vision-Language Pre-training based Product Retrieval in Taobao Search
Given a user query, the retrieval phase returns a subset of candidate products for the following ranking phase.
DoubleH: Twitter User Stance Detection via Bipartite Graph Neural Networks
Subsequently, we propose a bipartite graph neural network model, DoubleH, which aims to better utilize homogeneous and heterogeneous information in user stance detection tasks.
Structure-Informed Shadow Removal Networks
Hence, in this paper, we propose to remove shadows at the image structure level.
Learning Image Harmonization in the Linear Color Space
In this paper, we propose a novel neural approach to harmonize the image colors in a camera-independent color space, in which color values are proportional to the scene radiance.
Adaptive Illumination Mapping for Shadow Detection in Raw Images
In this paper, we propose a novel method to detect shadows from raw images.
Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence
In this paper, we take the role of investigators who want to trace the attack and identify the source, that is, the particular model which the adversarial examples are generated from.
Differentially Private Learning with Per-Sample Adaptive Clipping
As one way to implement privacy-preserving AI, differentially private learning is a framework that enables AI models to use differential privacy (DP).
Novel Modelling Strategies for High-frequency Stock Trading Data
Full electronic automation in stock exchanges has recently become popular, generating high-frequency intraday data and motivating the development of near real-time price forecasting methods.
3D-QueryIS: A Query-based Framework for 3D Instance Segmentation
Previous top-performing methods for 3D instance segmentation often maintain inter-task dependencies and the tendency towards a lack of robustness.
Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report
The role of mobile cameras increased dramatically over the past few years, leading to more and more research in automatic image quality enhancement and RAW photo processing.
Local Color Distributions Prior for Image Enhancement
Existing image enhancement methods are typically designed to address either the over- or under-exposure problem in the input image.
Ranked #1 on
Image Enhancement
on Exposure-Errors
Robust Offline Reinforcement Learning with Gradient Penalty and Constraint Relaxation
A promising paradigm for offline reinforcement learning (RL) is to constrain the learned policy to stay close to the dataset behaviors, known as policy constraint offline RL.
FedDef: Defense Against Gradient Leakage in Federated Learning-based Network Intrusion Detection Systems
Deep learning (DL) methods have been widely applied to anomaly-based network intrusion detection system (NIDS) to detect malicious traffic.
Boosting Night-time Scene Parsing with Learnable Frequency
Based on this, we propose to exploit the image frequency distributions for night-time scene parsing.
Quantized Adaptive Subgradient Algorithms and Their Applications
Therefore, a threshold quantization strategy with a relatively small error is adopted in QCMD adagrad and QRDA adagrad to improve the signal-to-noise ratio and preserve the sparsity of the model.
PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patch
Despite the diversity in attack patterns, adversarial patches tend to be highly textured and different in appearance from natural images.
Harmonizer: Learning to Perform White-Box Image and Video Harmonization
Unlike prior methods that are based on black-box autoencoders, Harmonizer contains a neural network for filter argument prediction and several white-box filters (based on the predicted arguments) for image harmonization.
Ranked #7 on
Image Harmonization
on iHarmony4
Structural Entropy Guided Graph Hierarchical Pooling
In addition to SEP, we further design two classification models, SEP-G and SEP-N for graph classification and node classification, respectively.
A Simple yet Effective Method for Graph Classification
Inspired by structural entropy on graphs, we transform the data sample from graphs to coding trees, which is a simpler but essential structure for graph data.
Multi-scale Attention Flow for Probabilistic Time Series Forecasting
The probability prediction of multivariate time series is a notoriously challenging but practical task.
CoupleFace: Relation Matters for Face Recognition Distillation
In this work, we observe that mutual relation knowledge between samples is also important to improve the discriminative ability of the learned representation of the student model, and propose an effective face recognition distillation method called CoupleFace by additionally introducing the Mutual Relation Distillation (MRD) into existing distillation framework.
Bi-directional Object-context Prioritization Learning for Saliency Ranking
We observe that spatial attention works concurrently with object-based attention in the human visual recognition system.
Rethinking Efficient Lane Detection via Curve Modeling
This paper presents a novel parametric curve-based method for lane detection in RGB images.
Ranked #2 on
Lane Detection
on LLAMAS
Interactive Data Analysis with Next-step Natural Language Query Recommendation
Natural language interfaces (NLIs) provide users with a convenient way to interactively analyze data through natural language queries.
ISDNet: Integrating Shallow and Deep Networks for Efficient Ultra-High Resolution Segmentation
The huge burden of computation and memory are two obstacles in ultra-high resolution image segmentation.
Adaptive Channel Encoding Transformer for Point Cloud Analysis
Transformer plays an increasingly important role in various computer vision areas and remarkable achievements have also been made in point cloud analysis.
Adaptive Channel Encoding for Point Cloud Analysis
Attention mechanism plays a more and more important role in point cloud analysis and channel attention is one of the hotspots.
Geometry-aware Two-scale PIFu Representation for Human Reconstruction
Our key idea is to exploit the complementary properties of depth denoising and 3D reconstruction, for learning a two-scale PIFu representation to reconstruct high-frequency facial details and consistent bodies separately.
Mitigating Adversarial Attacks by Distributing Different Copies to Different Users
We point out that by distributing different copies of the model to different buyers, we can mitigate the attack such that adversarial samples found on one copy would not work on another copy.
Gait Identification under Surveillance Environment based on Human Skeleton
Most existing gait identification methods extract features from gait videos and identify a probe sample by a query in the gallery.
Learning to Detect Instance-level Salient Objects Using Complementary Image Labels
However, it is non-trivial to use only class labels to learn instance-aware saliency information, as salient instances with high semantic affinities may not be easily separated by the labels.
Value Penalized Q-Learning for Recommender Systems
To alleviate the action distribution shift problem in extracting RL policy from static trajectories, we propose Value Penalized Q-learning (VPQ), an uncertainty-based offline RL algorithm.
Hierarchical information matters: Text classification via tree based graph neural network
Inspired by the structural entropy, we construct the coding tree of the graph by minimizing the structural entropy and propose HINT, which aims to make full use of the hierarchical information contained in the text for the task of text classification.
Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression
Recent studies on compression of pretrained language models (e. g., BERT) usually use preserved accuracy as the metric for evaluation.
Structural Optimization Makes Graph Classification Simpler and Better
We then present an implementation of the scheme in a tree kernel and a convolutional network to perform graph classification.
Dual-Neighborhood Deep Fusion Network for Point Cloud Analysis
To handle this prob-lem, a feature representation learning method, named Dual-Neighborhood Deep Fusion Network (DNDFN), is proposed to serve as an improved point cloud encoder for the task of non-idealized point cloud classification.
Realtime Robust Malicious Traffic Detection via Frequency Domain Analysis
To this end, we propose Whisper, a realtime ML based malicious traffic detection system that achieves both high accuracy and high throughput by utilizing frequency domain features.
AdaptCL: Efficient Collaborative Learning with Dynamic and Adaptive Pruning
In a highly heterogeneous environment, AdaptCL achieves a training speedup of 6. 2x with a slight loss of accuracy.
Learning to Sample Replacements for ELECTRA Pre-Training
Moreover, we propose to use a focal loss for the generator in order to relieve oversampling of correct tokens as replacements.
An Efficient Approach for Cross-Silo Federated Learning to Rank
Traditional learning-to-rank (LTR) models are usually trained in a centralized approach based upon a large amount of data.
Price graphs: Utilizing the structural information of financial time series for stock prediction
Then, structural information, referring to associations among temporal points and the node weights, is extracted from the mapped graphs to resolve the problems regarding long-range dependencies and the chaotic property.
Exploring Memorization in Adversarial Training
In this paper, we explore the memorization effect in adversarial training (AT) for promoting a deeper understanding of model capacity, convergence, generalization, and especially robust overfitting of the adversarially trained models.
CoSQA: 20,000+ Web Queries for Code Search and Question Answering
Finding codes given natural language query isb eneficial to the productivity of software developers.
Voice2Mesh: Cross-Modal 3D Face Model Generation from Voices
This work focuses on the analysis that whether 3D face models can be learned from only the speech inputs of speakers.
Blow the Dog Whistle: A Chinese Dataset for Cant Understanding with Common Sense and World Knowledge
Cant is important for understanding advertising, comedies and dog-whistle politics.
Excited state fluid mechanics and mathematical principles of separation and transition
Hitherto, separation and transition problems have not been described accurately in mathematical terms, leading to design errors and prediction problems in fluid machine engineering.
Fluid Dynamics
Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting
In this paper, we generalize text infilling (e. g., masked language models) by proposing Sequence Span Rewriting (SSR) as a self-supervised sequence-to-sequence (seq2seq) pre-training objective.
Mitigating Intensity Bias in Shadow Detection via Feature Decomposition and Reweighting
These two phenomenons reveal that deep shadow detectors heavily depend on the intensity cue, which we refer to as intensity bias.
Improving BERT with Syntax-aware Local Attention
Pre-trained Transformer-based neural language models, such as BERT, have achieved remarkable results on varieties of NLP tasks.
Location-aware Single Image Reflection Removal
It is beneficial to strong reflection detection and substantially improves the quality of reflection removal results.
GDA-HIN: A Generalized Domain Adaptive Model across Heterogeneous Information Networks
Domain adaptation using graph-structured networks learns label-discriminative and network-invariant node embeddings by sharing graph parameters.
Investigating Learning Dynamics of BERT Fine-Tuning
The recently introduced pre-trained language model BERT advances the state-of-the-art on many NLP tasks through the fine-tuning approach, but few studies investigate how the fine-tuning process improves the model performance on downstream tasks.
Robust Attacks on Deep Learning Face Recognition in the Physical World
Deep neural networks (DNNs) have been increasingly used in face recognition (FR) systems.
Exact Phase Transitions of Model RB with Slower-Growing Domains
The second moment method has always been an effective tool to lower bound the satisfiability threshold of many random constraint satisfaction problems.
Weakly-supervised Salient Instance Detection
Inspired by this insight, we propose to use class and subitizing labels as weak supervision for the SID problem.
Towards Ground Truth Explainability on Tabular Data
In data science, there is a long history of using synthetic data for method development, feature selection and feature engineering.
Relation-Aware Transformer for Portfolio Policy Learning
One of the key issues is how to represent the non-stationary price series of assets in a portfolio, which is important for portfolio decisions.
BERT Loses Patience: Fast and Robust Inference with Early Exit
In this paper, we propose Patience-based Early Exit, a straightforward yet effective inference method that can be used as a plug-and-play technique to simultaneously improve the efficiency and robustness of a pretrained language model (PLM).
Learning to Restore Low-Light Images via Decomposition-and-Enhancement
While concurrently enhancing a low-light image and removing its noise is ill-posed, we observe that noise exhibits different levels of contrast in different frequency layers, and it is much easier to detect noise in the lowfrequency layer than in the high one.
Synchrotron Microtomography and Neutron Radiography Characterization of the Microstruture and Water Absorption of Concrete from Pompeii
In the present work, samples were drilled from the "Hospitium" in Pompeii and were analyzed by synchrotron microtomography (uCT) and neutron radiography to study how the microstructure, including the presence of induced cracks, affects their water adsorption.
Applied Physics Materials Science Geophysics
Harvesting and Refining Question-Answer Pairs for Unsupervised QA
Our approach outperforms previous unsupervised approaches by a large margin and is competitive with early supervised models.
Ranked #189 on
Question Answering
on SQuAD1.1
Scheduled DropHead: A Regularization Method for Transformer Models
In this paper, we introduce DropHead, a structured dropout method specifically designed for regularizing the multi-head attention mechanism, which is a key component of transformer, a state-of-the-art model for various NLP tasks.
Self-Attention Attribution: Interpreting Information Interactions Inside Transformer
The great success of Transformer-based models benefits from the powerful multi-head self-attention mechanism, which learns token dependencies and encodes contextual information from the input.
Night-time Scene Parsing with a Large Real Dataset
Although huge progress has been made on scene analysis in recent years, most existing works assume the input images to be in day-time with good lighting conditions.
Learning to Compare for Better Training and Evaluation of Open Domain Natural Language Generation Models
While able to be trained in a fully self-supervised fashion, our model can be further fine-tuned with a little amount of human preference annotation to better imitate human judgment.
Self-Adversarial Learning with Comparative Discrimination for Text Generation
Conventional Generative Adversarial Networks (GANs) for text generation tend to have issues of reward sparsity and mode collapse that affect the quality and diversity of generated samples.
Pseudo-Bidirectional Decoding for Local Sequence Transduction
PBD copies the corresponding representation of source tokens to the decoder as pseudo future context to enable the decoder to attends to its bi-directional context.
DeepMask: an algorithm for cloud and cloud shadow detection in optical satellite remote sensing images using deep residual network
The average accuracy is 93. 56%, compared with 85. 36% from CFMask.
Improving Grammatical Error Correction with Machine Translation Pairs
The poor translation model resembles the ESL (English as a second language) learner and tends to generate translations of low quality in terms of fluency and grammatical correctness, while the good translation model generally generates fluent and grammatically correct translations.
Personalized Graph Neural Networks with Attention Mechanism for Session-Aware Recommendation
The other is Dot-Product Attention mechanism, which draws on the Transformer net to explicitly model the effect of historical sessions on the current session.
Online monitoring for safe pedestrian-vehicle interactions
As autonomous systems begin to operate amongst humans, methods for safe interaction must be investigated.
Robotics Multiagent Systems Signal Processing
Where Is My Mirror?
To the best of our knowledge, this is the first work to address the mirror segmentation problem with a computational approach.
DRFN: Deep Recurrent Fusion Network for Single-Image Super-Resolution with Large Factors
Recently, single-image super-resolution has made great progress owing to the development of deep convolutional neural networks (CNNs).
Visualizing and Understanding the Effectiveness of BERT
Language model pre-training, such as BERT, has achieved remarkable results in many NLP tasks.
Multi-Level Order-Flow Imbalance in a Limit Order Book
We study the multi-level order-flow imbalance (MLOFI), which is a vector quantity that measures the net flow of buy and sell orders at different price levels in a limit order book (LOB).
BERT-based Lexical Substitution
Our approach first applies dropout to the target word{'}s embedding for partially masking the word, allowing BERT to take balanced consideration of the target word{'}s semantics and contexts for proposing substitute candidates, and then validates the candidates based on their substitution{'}s influence on the global contextualized representation of the sentence.
Incremental training of multi-generative adversarial networks
Generative neural networks map a standard, possibly distribution to a complex high-dimensional distribution, which represents the real world data set.
Globally Soft Filter Pruning For Efficient Convolutional Neural Networks
Therefore, accumulating the saliency of the filter over the entire data set can provide more accurate guidance for pruning.
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset
Second, to better cover the stochastic distribution of real rain streaks, we propose a novel SPatial Attentive Network (SPANet) to remove rain streaks in a local-to-global manner.
Ranked #3 on
Single Image Deraining
on RainCityscapes
Active Matting
Our aim is to discover the most informative sequence of regions for user input in order to produce a good alpha matte with minimum labeling efforts.
Revisiting Image-Language Networks for Open-ended Phrase Detection
Most existing work that grounds natural language phrases in images starts with the assumption that the phrase in question is relevant to the image.
Image Correction via Deep Reciprocating HDR Transformation
Given an input LDR image, we first reconstruct the missing details in the HDR domain.
Diversified Top-k Partial MaxSAT Solving
We introduce a diversified top-k partial MaxSAT problem, a combination of partial MaxSAT problem and enumeration problem.
Learning to Generate Product Reviews from Attributes
This paper presents an attention-enhanced attribute-to-sequence model to generate product reviews for given attribute information, such as user, product, and rating.
Learning Influence Functions from Incomplete Observations
We establish both proper and improper PAC learnability of influence functions under randomly missing observations.
Word Network Topic Model: A Simple but General Solution for Short and Imbalanced Texts
The short text has been the prevalent format for information of Internet in recent decades, especially with the development of online social media, whose millions of users generate a vast number of short messages everyday.
A Statistical Parsing Framework for Sentiment Classification
Unlike previous works that employ syntactic parsing results for sentiment analysis, we develop a statistical parser to directly analyze the sentiment structure of a sentence.
