Search Results for author:
Found 109 papers, 40 papers with code
Robust Preference Optimization with Provable Noise Tolerance for LLMs
The preference alignment aims to enable large language models (LLMs) to generate responses that conform to human values, which is essential for developing general AI systems.
Scene Adaptive Sparse Transformer for Event-based Object Detection
However, they display inadequate sparsity and adaptability when applied to event-based object detection, since these approaches cannot balance the fine granularity of token-level sparsification and the efficiency of window-based Transformers, leading to reduced performance and efficiency.
Object Segmentation-Assisted Inter Prediction for Versatile Video Coding
Moreover, segmentation mask is considered in the joint rate-distortion optimization for motion estimation and partition estimation to derive the motion vector of different regions and partition more accurately.
Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling
To the best of our knowledge, SKR is the first attempt to address the time-consuming nature of data generation for learning neural operators.
Graph Relation Distillation for Efficient Biomedical Instance Segmentation
IGD constructs a graph representing instance features and relations, transferring these two types of knowledge by enforcing instance graph consistency.
Learning Multimodal Volumetric Features for Large-Scale Neuron Tracing
In this work, we aim to reduce human workload by predicting connectivity between over-segmented neuron pieces, taking both microscopy image and 3D morphology features into account, similar to human proofreading workflow.
Harmonizing SO(3)-Equivariance with Neural Expressiveness: a Hybrid Deep Learning Framework Oriented to the Prediction of Electronic Structure Hamiltonian
Deep learning for predicting the electronic structure Hamiltonian of quantum systems necessitates satisfying the covariance laws, among which achieving SO(3)-equivariance without sacrificing the non-linear expressive capability of networks remains unsolved.
Towards Decentralized Task Offloading and Resource Allocation in User-Centric Mobile Edge Computing
In the traditional cellular-based mobile edge computing (MEC), users at the edge of the cell are prone to suffer severe inter-cell interference and signal attenuation, leading to low throughput even transmission interruptions.
Promoting Generalization for Exact Solvers via Adversarial Instance Augmentation
To tackle this problem, we propose a novel approach, which is called Adversarial Instance Augmentation and does not require to know the problem type for new instance generation, to promote data diversity for learning-based branching modules in the branch-and-bound (B&B) Solvers (AdaSolver).
Accelerate Presolve in Large-Scale Linear Programming via Reinforcement Learning
Specifically, we formulate the routine design task as a Markov decision process and propose an RL framework with adaptive action sequences to generate high-quality presolve routines efficiently.
A Deep Instance Generative Framework for MILP Solvers Under Limited Data Availability
In the past few years, there has been an explosive surge in the use of machine learning (ML) techniques to address combinatorial optimization (CO) problems, especially mixed-integer linear programs (MILPs).
GET: Group Event Transformer for Event-Based Vision
Event cameras are a type of novel neuromorphic sen-sor that has been gaining increasing attention.
Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias
The inverse mapping leads to an objective function that is equivalent to that by the joint training, while it can effectively incorporate GNNs in the training phase of NEs against the learning bias.
Ranked #1 on
Node Property Prediction
on ogbn-proteins
Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation
In addition, our method also achieves state-of-the-art weakly supervised semantic segmentation performance on the PASCAL VOC 2012 and MS COCO 2014 datasets.
Learning Complete Topology-Aware Correlations Between Relations for Inductive Link Prediction
This implies the great potential of the semantic correlations for the entity-independent inductive link prediction task.
A Circuit Domain Generalization Framework for Efficient Logic Synthesis in Chip Design
In particular, we notice that the runtime of the Resub and Mfs2 operators often dominates the overall runtime of LS optimization processes.
DocMAE: Document Image Rectification via Self-supervised Representation Learning
Tremendous efforts have been made on document image rectification, but how to learn effective representation of such distorted images is still under-explored.
Adaptive Spot-Guided Transformer for Consistent Local Feature Matching
To deal with the above issues, we propose Adaptive Spot-Guided Transformer (ASTR) for local feature matching, which jointly models the local consistency and scale variations in a unified coarse-to-fine architecture.
Provably Convergent Subgraph-wise Sampling for Fast GNN Training
During the message passing (MP) in GNNs, subgraph-wise sampling methods discard messages outside the mini-batches in backward passes to avoid the well-known neighbor explosion problem, i. e., the exponentially increasing dependencies of nodes with the number of MP iterations.
Low-discrepancy Sampling in the Expanded Dimensional Space: An Acceleration Technique for Particle Swarm Optimization
The acceleration technique can generate a low-discrepancy sample set with a smaller dispersion, compared with a random sampling, in the expanded dimensional space; it also reduces the error at each iteration, and hence improves the convergence speed.
Energy-Efficient Blockchain-enabled User-Centric Mobile Edge Computing
To achieve efficient and reliable resource utilization with user-centric services, we propose an energy efficient blockchain-enabled UC-MEC system where blockchain operations and resource optimization are jointly performed.
Joint Optimization of Base Station Clustering and Service Caching in User-Centric MEC
To address single-base station (BS) transmission limitation and serious edge effect in traditional cellular-based edge service caching networks, in this paper, we proposed a novel user-centric edge service caching framework where each user is jointly provided with edge caching and wireless transmission services by a specific BS cluster instead of a single BS.
Generalization in Visual Reinforcement Learning with the Reward Sequence Distribution
The appealing features of RSD-OA include that: (1) RSD-OA is invariant to visual distractions, as it is conditioned on the predefined subsequent action sequence without task-irrelevant information from transition dynamics, and (2) the reward sequence captures long-term task-relevant information in both rewards and transition dynamics.
Effective Multimodal Reinforcement Learning with Modality Alignment and Importance Enhancement
Specifically, we observe that these issues make conventional RL methods difficult to learn a useful state representation in the end-to-end training with multimodal information.
De Novo Molecular Generation via Connection-aware Motif Mining
The obtained motif vocabulary consists of not only molecular motifs (i. e., the frequent fragments), but also their connection information, indicating how the motifs are connected with each other.
Learning Cut Selection for Mixed-Integer Linear Programming via Hierarchical Sequence Model
Cut selection -- which aims to select a proper subset of the candidate cuts to improve the efficiency of solving MILPs -- heavily depends on (P1) which cuts should be preferred, and (P2) how many cuts should be selected.
Camouflaged Instance Segmentation via Explicit De-Camouflaging
To address these challenges, we propose a novel De-camouflaging Network (DCNet) including a pixel-level camouflage decoupling module and an instance-level camouflage suppression module.
D2Former: Jointly Learning Hierarchical Detectors and Contextual Descriptors via Agent-Based Transformers
Second, the HKDL module can generate keypoint detectors in a hierarchical way, which is helpful for detecting keypoints with diverse levels of structures.
Learning Cross-Representation Affinity Consistency for Sparsely Supervised Biomedical Instance Segmentation
Sparse instance-level supervision has recently been explored to address insufficient annotation in biomedical instance segmentation, which is easier to annotate crowded instances and better preserves instance completeness for 3D volumetric datasets compared to common semi-supervision. In this paper, we propose a sparsely supervised biomedical instance segmentation framework via cross-representation affinity consistency regularization.
DualRel: Semi-Supervised Mitochondria Segmentation From a Prototype Perspective
Automatic mitochondria segmentation enjoys great popularity with the development of deep learning.
Alignment Before Aggregation: Trajectory Memory Retrieval Network for Video Object Segmentation
In this work, we reconcile the inherent tension of spatial and temporal information to retrieve memory frame information along the object trajectory, and propose a novel and coherent Trajectory Memory Retrieval Network (TMRN) to equip with the trajectory information, including a spatial alignment module and a temporal aggregation module.
Autothrottle: A Practical Bi-Level Approach to Resource Management for SLO-Targeted Microservices
We present Autothrottle, a bi-level resource management framework for microservices with latency SLOs (service-level objectives).
Research on Self-adaptive Online Vehicle Velocity Prediction Strategy Considering Traffic Information Fusion
In order to increase the prediction accuracy of the online vehicle velocity prediction (VVP) strategy, a self-adaptive velocity prediction algorithm fused with traffic information was presented for the multiple scenarios.
Updating velocities in heterogeneous comprehensive learning particle swarm optimization with low-discrepancy sequences
Heterogeneous comprehensive learning particle swarm optimization (HCLPSO) is a type of evolutionary algorithm with enhanced exploration and exploitation capabilities.
Model-Guided Multi-Contrast Deep Unfolding Network for MRI Super-resolution Reconstruction
Interpretable neural network models are of significant interest since they enhance the trustworthiness required in clinical practice when dealing with medical images.
Modeling Diverse Chemical Reactions for Single-step Retrosynthesis via Discrete Latent Variables
The goal of single-step retrosynthesis is to identify the possible reactants that lead to the synthesis of the target product in one reaction.
Meta Reinforcement Learning with Successor Feature Based Context
Most reinforcement learning (RL) methods only focus on learning a single task from scratch and are not able to use prior knowledge to learn other tasks more effectively.
Automatic Reward Design via Learning Motivation-Consistent Intrinsic Rewards
In this paper, we propose to automatically generate goal-consistent intrinsic rewards for the agent to learn, by maximizing which the expected accumulative extrinsic rewards can be maximized.
Towards Hybrid-Optimization Video Coding
Our idea is to provide multiple discrete starting points in the global space and optimize the local optimum around each point by numerical algorithm efficiently.
Self-Adaptive Label Augmentation for Semi-supervised Few-shot Classification
A major novelty of SALA is the task-adaptive metric, which can learn the metric adaptively for different tasks in an end-to-end fashion.
Exploiting Global Semantic Similarities in Knowledge Graphs by Relational Prototype Entities
By enforcing the entities' embeddings close to their associated prototypes' embeddings, our approach can effectively encourage the global semantic similarities of entities -- that can be far away in the KG -- connected by the same relation.
Feudal Multi-Agent Reinforcement Learning with Adaptive Network Partition for Traffic Signal Control
To do this, we propose two approaches: one is directly to use graph neural network (GNN) to generate the network partition, and the other is to use Monte-Carlo tree search (MCTS) to find the best partition with criteria computed by GNN.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Compressing Deep Graph Neural Networks via Adversarial Knowledge Distillation
To tackle these problems, we propose a novel Adversarial Knowledge Distillation framework for graph models named GraphAKD, which adversarially trains a discriminator and a generator to adaptively detect and decrease the discrepancy.
Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions
Generalization across different environments with the same tasks is critical for successful applications of visual reinforcement learning (RL) in real scenarios.
MNL-Bandits under Inventory and Limited Switches Constraints
Optimizing the assortment of products to display to customers is a key to increasing revenue for both offline and online retailers.
Duality-Induced Regularizer for Semantic Matching Knowledge Graph Embeddings
Semantic matching models -- which assume that entities with similar semantics have similar embeddings -- have shown great power in knowledge graph embeddings (KGE).
ProgressiveMotionSeg: Mutually Reinforced Framework for Event-Based Motion Segmentation
Dynamic Vision Sensor (DVS) can asynchronously output the events reflecting apparent motion of objects with microsecond resolution, and shows great application potential in monitoring and other fields.
HIPA: Hierarchical Patch Transformer for Single Image Super Resolution
Transformer-based architectures start to emerge in single image super resolution (SISR) and have achieved promising performance.
Rethinking Graph Convolutional Networks in Knowledge Graph Completion
Surprisingly, we observe from experiments that the graph structure modeling in GCNs does not have a significant impact on the performance of KGC models, which is in contrast to the common belief.
Towards 3D Scene Reconstruction from Locally Scale-Aligned Monocular Video Depth
However, in some video-based scenarios such as video depth estimation and 3D scene reconstruction from a video, the unknown scale and shift residing in per-frame prediction may cause the depth inconsistency.
Motion-Modulated Temporal Fragment Alignment Network for Few-Shot Action Recognition
To address this issue, we propose an end-to-end Motion-modulated Temporal Fragment Alignment Network (MTFAN) by jointly exploring the task-specific motion modulation and the multi-level temporal fragment alignment for Few-Shot Action Recognition (FSAR).
Multi-Grained Spatio-Temporal Features Perceived Network for Event-Based Lip-Reading
To recognize words from the event data, we propose a novel Multi-grained Spatio-Temporal Features Perceived Network (MSTP) to perceive fine-grained spatio-temporal features from microsecond time-resolved event data.
Integrating Quantum Processor Device and Control Optimization in a Gradient-based Framework
In a quantum processor, the device design and external controls together contribute to the quality of the target quantum operations.
An effective hybrid search algorithm for the multiple traveling repairman problem with profits
As an extension of the traveling repairman problem with profits, the multiple traveling repairman problem with profits consists of multiple repairmen who visit a subset of all customers to maximize the revenues collected through the visited customers.
ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs
To address this challenge, we propose a novel query embedding model, namely Cone Embeddings (ConE), which is the first geometry-based QE model that can handle all the FOL operations, including conjunction, disjunction, and negation.
End-to-End Image Compression with Probabilistic Decoding
However, this nature was seldom considered in previous studies on image compression, which usually chose one possible image as reconstruction, e. g. the one with the maximal a posteriori probability.
VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows
Different from visible cameras which record intensity images frame by frame, the biologically inspired event camera produces a stream of asynchronous and sparse events with much lower latency.
Ranked #1 on
Object Tracking
on VisEvent
MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking
The visible and thermal filters will be used to conduct a dynamic convolutional operation on their corresponding input feature maps respectively.
Ranked #17 on
Rgb-T Tracking
on RGBT234
Disentangle Your Dense Object Detector
Extensive experiments on MS COCO benchmark show that our approach can lead to 2. 0 mAP, 2. 4 mAP and 2. 2 mAP absolute improvements on RetinaNet, FCOS, and ATSS baselines with negligible extra overhead.
Uncertainty Guided Collaborative Training for Weakly Supervised Temporal Action Detection
To alleviate this problem, we propose a novel Uncertainty Guided Collaborative Training (UGCT) strategy, which mainly includes two key designs: (1) The first design is an online pseudo label generation module, in which the RGB and FLOW streams work collaboratively to learn from each other.
Lesion-Aware Transformers for Diabetic Retinopathy Grading
First, to the best of our knowledge, this is the first work to formulate lesion discovery as a weakly supervised lesion localization problem via a transformer decoder.
Tracking by Joint Local and Global Search: A Target-aware Attention based Approach
In this paper, we propose a novel and general target-aware attention mechanism (termed TANet) and integrate it with tracking-by-detection framework to conduct joint local and global search for robust tracking.
Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer
To address these issues, we propose a novel end-to-end Part-Aware Transformer (PAT) for occluded person Re-ID through diverse part discovery via a transformer encoderdecoder architecture, including a pixel context based transformer encoder and a part prototype based transformer decoder.
MVT: Mask Vision Transformer for Facial Expression Recognition in the wild
Facial Expression Recognition (FER) in the wild is an extremely challenging task in computer vision due to variant backgrounds, low-quality facial images, and the subjectiveness of annotators.
Facial Expression Recognition
Facial Expression Recognition (FER)
Action Unit Memory Network for Weakly Supervised Temporal Action Localization
In this paper, we present an Action Unit Memory Network (AUMN) for weakly supervised temporal action localization, which can mitigate the above two challenges by learning an action unit memory bank.
Ranked #7 on
Weakly Supervised Action Localization
on THUMOS14
Weakly Supervised Action Localization
Weakly-supervised Temporal Action Localization
+1
Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark
We believe this benchmark will greatly boost related researches on natural language guided tracking.
Ranked #3 on
Visual Object Tracking
on TNL2K
(precision metric)
Dynamic Attention guided Multi-Trajectory Analysis for Single Object Tracking
In this paper, we propose to introduce more dynamics by devising a dynamic attention-guided multi-trajectory tracking strategy.
Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphs
TACT is inspired by the observation that the semantic correlation between two relations is highly correlated to their topological structure in knowledge graphs.
Foreground Activation Maps for Weakly Supervised Object Localization
To the best of our knowledge, this is the first work that can achieve remarkable performance for both tasks by optimizing them jointly via FAM for WSOL.
Task-Aware Part Mining Network for Few-Shot Learning
The task-aware part filters can adapt to any individual task and automatically mine task-related local parts even for an unseen task.
Learning to Utilize Shaping Rewards: A New Approach of Reward Shaping
In this paper, we consider the problem of adaptively utilizing a given shaping reward function.
SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis
In particular, the prediction of aspect-sentiment pairs is converted into multi-label classification, aiming to capture the dependency between words in a pair.
Ranked #14 on
Stock Market Prediction
on Astock
Camera Trace Erasing
To reconcile these two demands, we propose Siamese Trace Erasing (SiamTE), in which a novel hybrid loss is designed on the basis of Siamese architecture for network training.
Multi-Agent Deep Reinforcement Learning with Adaptive Policies
To tackle this, we propose to train multiple policies for each agent and postpone the selection of the best policy at execution time.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Progressive Retinex: Mutually Reinforced Illumination-Noise Perception Network for Low Light Image Enhancement
Contrast enhancement and noise removal are coupled problems for low-light image enhancement.
LinesToFacePhoto: Face Photo Generation from Lines with Conditional Self-Attention Generative Adversarial Network
The large-scale discriminator enforces the completeness of global structures and the small-scale discriminator encourages fine details, thereby enhancing the realism of generated face images.
Knowledge Transfer via Student-Teacher Collaboration
One way to compress these heavy models is knowledge transfer (KT), in which a light student network is trained through absorbing the knowledge from a powerful teacher network.
Evaluating Pest Management Strategies: A Robust Method and its Application to Strawberry Disease Management
The objective of our study is to propose a methodology to address the issue of an insufficient number of observations using simulations and take into account the effect of disease pressure on yield through a quantile regression model.
Context-Aware Visual Policy Network for Fine-Grained Image Captioning
With the maturity of visual detection techniques, we are more ambitious in describing visual content with open-vocabulary, fine-grained and free-form language, i. e., the task of image captioning.
Deep Learning-Based Video Coding: A Review and A Case Study
For deep schemes, pixel probability modeling and auto-encoder are the two approaches, that can be viewed as predictive coding scheme and transform coding scheme, respectively.
Multimedia Image and Video Processing
Camera Lens Super-Resolution
Existing methods for single image super-resolution (SR) are typically evaluated with synthetic degradation models such as bicubic or Gaussian downsampling.
Learning Deterministic Policy with Target for Power Control in Wireless Networks
DRL-DPT overcomes the main obstacles in applying reinforcement learning and deep learning in wireless networks, i. e. continuous state space, continuous action space and convergence.
Sequential Gating Ensemble Network for Noise Robust Multi-Scale Face Restoration
The SGU sequentially takes information from two different levels as inputs and decides the output based on one active input.
Learning to Assemble Neural Module Tree Networks for Visual Grounding
In particular, we develop a novel modular network called Neural Module Tree network (NMTree) that regularizes the visual grounding along the dependency parsing tree of the sentence, where each node is a neural module that calculates visual attention according to its linguistic feature, and the grounding score is accumulated in a bottom-up direction where as needed.
A Deep Tree-Structured Fusion Model for Single Image Deraining
We propose a simple yet effective deep tree-structured fusion model based on feature aggregation for the deraining problem.
Deep Boosting for Image Denoising
Boosting is a classic algorithm which has been successfully applied to diverse computer vision tasks.
Context-Aware Visual Policy Network for Sequence-Level Image Captioning
To fill the gap, we propose a Context-Aware Visual Policy network (CAVP) for sequence-level image captioning.
A Two-Stream Mutual Attention Network for Semi-supervised Biomedical Segmentation with Noisy Labels
\begin{abstract} Learning-based methods suffer from a deficiency of clean annotations, especially in biomedical segmentation.
Towards Optimal Power Control via Ensembling Deep Neural Networks
A deep neural network (DNN) based power control method is proposed, which aims at solving the non-convex optimization problem of maximizing the sum rate of a multi-user interference channel.
Person Re-Identification With Cascaded Pairwise Convolutions
In this paper, a novel deep architecture named BraidNet is proposed for person re-identification.
Learning for Video Compression
One key challenge to learning-based video compression is that motion predictive coding, a very effective tool for video compression, can hardly be trained into a neural network.
Multimedia Image and Video Processing
Neural network-based arithmetic coding of intra prediction modes in HEVC
In this paper, we propose an arithmetic coding strategy by training neural networks, and make preliminary studies on coding of the intra prediction modes in HEVC.
Multimedia
An Iterative BP-CNN Architecture for Channel Decoding
The standard BP decoder is used to estimate the coded bits, followed by a CNN to remove the estimation errors of the BP decoder and obtain a more accurate estimation of the channel noise.
Snapshot Hyperspectral Light Field Imaging
This paper presents the first snapshot hyperspectral light field imager in practice.
A Convolutional Neural Network Approach for Half-Pel Interpolation in Video Coding
To further improve the coding efficiency, sub-pel motion compensation has been utilized, which requires interpolation of fractional samples.
Multimedia
Convolutional Neural Network-Based Block Up-sampling for Intra Frame Coding
A block can be down-sampled before being compressed by normal intra coding, and then up-sampled to its original resolution.
Multimedia
A Convolutional Neural Network Approach for Post-Processing in HEVC Intra Coding
Lossy image and video compression algorithms yield visually annoying artifacts including blocking, blurring, and ringing, especially at low bit-rates.
Multimedia
Understanding User Instructions by Utilizing Open Knowledge for Service Robots
Understanding user instructions in natural language is an active research topic in AI and robotics.
Deeply Exploit Depth Information for Object Detection
This paper addresses the issue on how to more effectively coordinate the depth with RGB aiming at boosting the performance of RGB-D object detection.
Learning High-level Prior with Convolutional Neural Networks for Semantic Segmentation
Finally, the optimization problem enables us to take advantage of state-of-the-art fully convolutional network structure for the implementation of the above encoders and decoder.
High-Speed Hyperspectral Video Acquisition With a Dual-Camera Architecture
We propose a novel dual-camera design to acquire 4D high-speed hyperspectral (HSHS) videos with high spatial and spectral resolution.
Separable Kernel for Image Deblurring
In this paper, we deal with the image deblurring problem in a completely new perspective by proposing separable kernel to represent the inherent properties of the camera and scene system.
CID: Combined Image Denoising in Spatial and Frequency Domains Using Web Images
Second, to handle heavy noise, we further propose using the denoising image to improve image registration of the retrieved Web images, 3D cube building, and the estimation of filtering parameters in the frequency domain.
Bayesian Mixture Modelling and Inference based Thompson Sampling in Monte-Carlo Tree Search
Monte-Carlo tree search is drawing great interest in the domain of planning under uncertainty, particularly when little or no domain knowledge is available.
Regret-Based Multi-Agent Coordination with Uncertain Task Rewards
Many multi-agent coordination problems can be represented as DCOPs.
Efficient 2D-to-3D Correspondence Filtering for Scalable 3D Object Recognition
3D model-based object recognition has been a noticeable research trend in recent years.
Depth Acquisition from Density Modulated Binary Patterns
First, we propose an algorithm to design the patterns to carry more phase information without compromising the depth reconstruction from a single captured image as with Kinect.
