Search Results for author:
Found 70 papers, 28 papers with code
Improving Empathetic Response Generation by Recognizing Emotion Cause in Conversations
The emotion cause is a stimulus for human emotions.
CRNet: A Detail-Preserving Network for Unified Image Restoration and Enhancement Task
In real-world scenarios, images captured often suffer from blurring, noise, and other forms of image degradation, and due to sensor limitations, people usually can only obtain low dynamic range images.
Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos
Federated learning (FL), aimed at leveraging vast distributed datasets, confronts a crucial challenge: the heterogeneity of data across different silos.
Meta-Task Prompting Elicits Embedding from Large Language Models
In this work, we introduce a new unsupervised embedding method, Meta-Task Prompting with Explicit One-Word Limitation (MetaEOL), for generating high-quality sentence embeddings from Large Language Models (LLMs) without the need for model fine-tuning or task-specific engineering.
Corpus-Steered Query Expansion with Large Language Models
Recent studies demonstrate that query expansions generated by large language models (LLMs) can considerably enhance information retrieval systems by generating hypothetical documents that answer the queries as expansions.
Transformer-based Selective Super-Resolution for Efficient Image Refinement
Conventional super-resolution methods suffer from two drawbacks: substantial computational cost in upscaling an entire large image, and the introduction of extraneous or potentially detrimental information for downstream computer vision tasks during the refinement of the background.
Patch-based Selection and Refinement for Early Object Detection
Early object detection (OD) is a crucial task for the safety of many dynamic systems.
Diversifying the Mixture-of-Experts Representation for Language Models with Orthogonal Optimizer
The Mixture of Experts (MoE) has emerged as a highly successful technique in deep learning, based on the principle of divide-and-conquer to maximize model capacity without significant additional computational cost.
Incremental Learning on Food Instance Segmentation
The power of the framework is a novel difficulty assessment model, which forecasts how challenging an unlabelled sample is to the latest trained instance segmentation model.
Unsupervised Dense Retrieval with Relevance-Aware Contrastive Pre-Training
Dense retrievers have achieved impressive performance, but their demand for abundant training data limits their application scenarios.
DETR-based Layered Clothing Segmentation and Fine-Grained Attribute Recognition
Clothing segmentation and fine-grained attribute recognition are challenging tasks at the crossing of computer vision and fashion, which segment the entire ensemble clothing instances as well as recognize detailed attributes of the clothing products from any input human images.
AnimeDiffusion: Anime Face Line Drawing Colorization via Diffusion Models
Through multiple quantitative metrics evaluated on our dataset and a user study, we demonstrate AnimeDiffusion outperforms state-of-the-art GANs-based models for anime face line drawing colorization.
Attention-Aware Anime Line Drawing Colorization
Automatic colorization of anime line drawing has attracted much attention in recent years since it can substantially benefit the animation industry.
TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack
We present Twin Answer Sentences Attack (TASA), an adversarial attack method for question answering (QA) models that produces fluent and grammatical adversarial contexts while maintaining gold answers.
SpikeSim: An end-to-end Compute-in-Memory Hardware Evaluation Tool for Benchmarking Spiking Neural Networks
To this end, we propose SpikeSim, a tool that can perform realistic performance, energy, latency and area evaluation of IMC-mapped SNNs.
On the Complementarity between Pre-Training and Random-Initialization for Resource-Rich Machine Translation
Pre-Training (PT) of text representations has been successfully applied to low-resource Neural Machine Translation (NMT).
FEC: Fast Euclidean Clustering for Point Cloud Segmentation
Segmentation from point cloud data is essential in many applications such as remote sensing, mobile robots, or autonomous cars.
DeePKS+ABACUS as a Bridge between Expensive Quantum Mechanical Models and Machine Learning Potentials
However, for high-level QM methods, such as density functional theory (DFT) at the meta-GGA level and/or with exact exchange, quantum Monte Carlo, etc., generating a sufficient amount of data for training a ML potential has remained computationally challenging due to their high cost.
Learning Optimal Flows for Non-Equilibrium Importance Sampling
On the theory side, we discuss how to tailor the velocity field to the target and establish general conditions under which the proposed estimator is a perfect estimator with zero-variance.
Interpretable Proof Generation via Iterative Backward Reasoning
We present IBR, an Iterative Backward Reasoning model to solve the proof generation tasks on rule-based Question Answering (QA), where models are required to reason over a series of textual rules and facts to find out the related proof path and derive the final answer.
Phrase-level Textual Adversarial Attack with Label Preservation
Generating high-quality textual adversarial examples is critical for investigating the pitfalls of natural language processing (NLP) models and further promoting their robustness.
COIN: Communication-Aware In-Memory Acceleration for Graph Convolutional Networks
Besides accelerating the computation using custom compute elements (CE) and in-memory computing, COIN aims at minimizing the intra- and inter-CE communication in GCN operations to optimize the performance and energy efficiency.
A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generation
To alleviate the above data issues, we propose a data manipulation method, which is model-agnostic to be packed with any persona-based dialogue generation model to improve its performance.
Bridging Cross-Lingual Gaps During Leveraging the Multilingual Sequence-to-Sequence Pretraining for Text Generation and Understanding
For multilingual sequence-to-sequence pretrained language models (multilingual Seq2Seq PLMs), e. g. mBART, the self-supervised pretraining task is trained on a wide range of monolingual languages, e. g. 25 languages from CommonCrawl, while the downstream cross-lingual tasks generally progress on a bilingual language subset, e. g. English-German, making there exists the data discrepancy, namely domain discrepancy, and cross-lingual learning objective discrepancy, namely task discrepancy, between the pretraining and finetuning stages.
A Knowledge-Based Decision Support System for In Vitro Fertilization Treatment
To improve the IVF success rate, we propose a knowledge-based decision support system that can provide medical advice on the treatment protocol and medication adjustment for each patient visit during IVF treatment cycle.
Dual-CLVSA: a Novel Deep Learning Approach to Predict Financial Markets with Sentiment Measurements
It is a challenging task to predict financial markets.
Swin-Pose: Swin Transformer Based Human Pose Estimation
We are interested in exploring its capability in human pose estimation, and thus propose a novel model based on transformer architecture, enhanced with a feature pyramid fusion structure.
A Joint Beamforming Design and Integrated CPM-LFM Signal for Dual-functional Radar-communication Systems
Similarly to the conception of communication rate, this paper defines radar rate to unify the DFRC system.
Plurality and Quantification in Graph Representation of Meaning
In this thesis we present a semantic representation formalism based on directed graphs and explore its linguistic adequacy and explanatory benefits in the semantics of plurality and quantification.
Serving DNN Models with Multi-Instance GPUs: A Case of the Reconfigurable Machine Scheduling Problem
With MIG, A100 can be the most cost-efficient GPU ever for serving Deep Neural Networks (DNNs).
SIAM: Chiplet-based Scalable In-Memory Acceleration with Mesh for Deep Neural Networks
In-memory computing (IMC) on a monolithic chip for deep learning faces dramatic challenges on area, yield, and on-chip interconnection cost due to the ever-increasing model sizes.
Underwater inspection and intervention dataset
This paper presents a novel dataset for the development of visual navigation and simultaneous localisation and mapping (SLAM) algorithms as well as for underwater intervention tasks.
Impact of On-Chip Interconnect on In-Memory Acceleration of Deep Neural Networks
In this technique, we use analytical models of NoC to evaluate end-to-end communication latency of any given DNN.
Alternate Model Growth and Pruning for Efficient Training of Recommendation Systems
Our method leverages structured sparsification to reduce computational cost without hurting the model capacity at the end of offline training so that a full-size model is available in the recurring training stage to learn new data in real-time.
CLVSA: A Convolutional LSTM Based Variational Sequence-to-Sequence Model with Attention for Predicting Trends of Financial Markets
Financial markets are a complex dynamical system.
Financial Markets Prediction with Deep Learning
Financial markets are difficult to predict due to its complex systems dynamics.
DAGN: Discourse-Aware Graph Network for Logical Reasoning
The model encodes discourse information as a graph with elementary discourse units (EDUs) and discourse relations, and learns the discourse-aware features via a graph network for downstream QA tasks.
Ranked #24 on
Reading Comprehension
on ReClor
RA-BNN: Constructing Robust & Accurate Binary Neural Network to Simultaneously Defend Adversarial Bit-Flip Attack and Improve Accuracy
Apart from recovering the inference accuracy, our RA-BNN after growing also shows significantly higher resistance to BFA.
Towards Efficiently Diversifying Dialogue Generation via Embedding Augmentation
Dialogue generation models face the challenge of producing generic and repetitive responses.
Colorectal Polyp Detection in Real-world Scenario: Design and Experiment Study
All these factors pose a significant challenge to effective polyp detection in a colonoscopy.
A Learning-Based Tune-Free Control Framework for Large Scale Autonomous Driving System Deployment
This paper presents the design of a tune-free (human-out-of-the-loop parameter tuning) control framework, aiming at accelerating large scale autonomous driving system deployed on various vehicles and driving environments.
Pretrained Language Models for Dialogue Generation with Multiple Input Sources
In this work, we study dialogue models with multiple input sources adapted from the pretrained language model GPT2.
A Progressive Sub-Network Searching Framework for Dynamic Inference
Many techniques have been developed, such as model compression, to make Deep Neural Networks (DNNs) inference more efficiently.
Retinopathy of Prematurity Stage Diagnosis Using Object Segmentation and Convolutional Neural Networks
This paper builds upon the success of previous models and develops a novel architecture, which combines object segmentation and convolutional neural networks (CNN) to construct an effective classifier of ROP stages 1-3 based on neonatal retinal images.
Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images
High-fidelity clothing reconstruction is the key to achieving photorealism in a wide range of applications including human digitization, virtual try-on, etc.
Pseudo-Labeling for Small Lesion Detection on Diabetic Retinopathy Images
The first one is that our dataset is not fully labeled, i. e., only a subset of all lesion instances are marked.
3D Aggregated Faster R-CNN for General Lesion Detection
This classifier branch is equipped with Feature Aggregation and Local Magnification Layers to enhance the classifier branch.
Colorectal Polyp Segmentation by U-Net with Dilation Convolution
The model we design consists of an encoder to extract multi-scale semantic features and a decoder to expand the feature maps to a polyp segmentation map.
Mini Lesions Detection on Diabetic Retinopathy Images via Large Scale CNN Features
We analyze the lesion-vs-image scale carefully and propose a large-size feature pyramid network (LFPN) to preserve more image details for mini lesion instance detection.
Unsupervised Domain Adaptation on Reading Comprehension
On the other hand, it further reduces domain distribution discrepancy through conditional adversarial learning across domains.
Structural Pruning in Deep Neural Networks: A Small-World Approach
Inspired by the observation that brain networks follow the Small-World model, we propose a novel structural pruning scheme, which includes (1) hierarchically trimming the network into a Small-World model before training, (2) training the network for a given dataset, and (3) optimizing the network for accuracy.
AFP-Net: Realtime Anchor-Free Polyp Detection in Colonoscopy
Though challenging, with the great advances in object detection techniques, automated polyp detection still demonstrates a great potential in reducing the false negative rate while maintaining a high precision.
Investigating BERT's Knowledge of Language: Five Analysis Methods with NPIs
We conclude that a variety of methods is necessary to reveal all relevant aspects of a model's grammatical knowledge in a given domain.
3D Anchor-Free Lesion Detector on Computed Tomography Scans
The anchor mechanism is removed and lesions are formalized as single keypoints.
A Deep Reinforcement Learning Approach to Multi-component Job Scheduling in Edge Computing
We are interested in the optimal scheduling of a collection of multi-component application jobs in an edge computing system that consists of geo-distributed edge computing nodes connected through a wide area network.
Multi-Stream Single Shot Spatial-Temporal Action Detection
We present a 3D Convolutional Neural Networks (CNNs) based single shot detector for spatial-temporal action detection tasks.
Automatic Compiler Based FPGA Accelerator for CNN Training
Training of convolutional neural networks (CNNs)on embedded platforms to support on-device learning is earning vital importance in recent days.
Single-Net Continual Learning with Progressive Segmented Training (PST)
Such a system requires learning from the data stream, training the model to preserve previous information and adapt to a new task, and generating a single-headed vector for future inference.
Towards Efficient Neural Networks On-a-chip: Joint Hardware-Algorithm Approaches
Machine learning algorithms have made significant advances in many applications.
Efficient Network Construction through Structural Plasticity
A typical training pipeline to mitigate over-parameterization is to pre-define a DNN structure first with redundant learning units (filters and neurons) under the goal of high accuracy, then to prune redundant learning units after training with the purpose of efficient inference.
CGaP: Continuous Growth and Pruning for Efficient Deep Learning
Today a canonical approach to reduce the computation cost of Deep Neural Networks (DNNs) is to pre-define an over-parameterized model before training to guarantee the learning capacity, and then prune unimportant learning units (filters and neurons) during training to improve model compactness.
BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering
Graph convolutional networks are used to obtain a relation-aware representation of nodes for entity graphs built from documents with multi-level features.
Large-Scale Neuromorphic Spiking Array Processors: A quest to mimic the brain
Neuromorphic engineering (NE) encompasses a diverse range of approaches to information processing that are inspired by neurobiological systems, and this feature distinguishes neuromorphic systems from conventional computing systems.
Generative Sensing: Transforming Unreliable Sensor Data for Reliable Recognition
The proposed generative sensing framework aims at transforming low-end, low-quality sensor data into higher quality sensor data in terms of achieved classification accuracy.
Algorithm and Hardware Design of Discrete-Time Spiking Neural Networks Based on Back Propagation with Binary Activations
We present a new back propagation based training algorithm for discrete-time spiking neural networks (SNN).
DeepDSL: A Compilation-based Domain-Specific Language for Deep Learning
In this paper, we present DeepDSL, a domain specific language (DSL) embedded in Scala, that compiles deep networks written in DeepDSL to Java source code.
DeepFood: Deep Learning-Based Food Image Recognition for Computer-Aided Dietary Assessment
We applied our proposed approach to two real-world food image data sets (UEC-256 and Food-101) and achieved impressive results.
Reducing the Model Order of Deep Neural Networks Using Information Theory
In this paper, we propose a method to compress deep neural networks by using the Fisher Information metric, which we estimate through a stochastic optimization method that keeps track of second-order information in the network.
Unsupervised Cross-Domain Recognition by Identifying Compact Joint Subspaces
By adopting a natural and widely used assumption -- "the data samples from the same class should lay on a low-dimensional subspace, even if they come from different domains", the proposed method circumvents the limitation of the global domain shift, and solves the cross-domain recognition by finding the compact joint subspaces of source and target domain.
Recognize Human Activities from Partially Observed Videos
In this paper, we propose a new method that can recognize human activities from partially observed videos in the general case.
