Search Results for author:
Found 194 papers, 62 papers with code
A Multi-modal one-class generative adversarial network for anomaly detection in manufacturing
Since the generated samples simulate the low density area for each modal, the discriminator could directly detect anomalies from normal data.
Unregulated Chinese-to-English Data Expansion Does NOT Work for Neural Event Detection
The survey of translations suggests that the mistakenly-aligned triggers in the expanded data negatively influences the retraining process.
Deep Tree-based Retrieval for Efficient Recommendation: Theory and Method
With the development of deep learning techniques, deep recommendation models also achieve remarkable improvements in terms of recommendation accuracy.
Multi-level Monte-Carlo Gradient Methods for Stochastic Optimization with Biased Oracles
This setting captures various optimization paradigms, such as conditional stochastic optimization, distributionally robust optimization, shortfall risk optimization, and machine learning paradigms, such as contrastive learning.
Multi-agent Multi-armed Bandits with Stochastic Sharable Arm Capacities
We also design an iterative distributed algorithm for players to commit to an optimal arm pulling profile with a constant number of rounds in expectation.
Regularization for Adversarial Robust Learning
We numerically validate our proposed method in supervised learning, reinforcement learning, and contextual learning and showcase its state-of-the-art performance against various adversarial attacks.
Chinese Metaphor Recognition Using a Multi-stage Prompting Large Language Model
Metaphors are common in everyday language, and the identification and understanding of metaphors are facilitated by models to achieve a better understanding of the text.
Learning Rule-Induced Subgraph Representations for Inductive Relation Prediction
Specifically, we propose a \textit{single-source} initialization approach to initialize edge features only for the target link, which guarantees the relevance of mined rules and target link.
SAM 2 in Robotic Surgery: An Empirical Evaluation for Robustness and Generalization in Surgical Video Segmentation
The recent Segment Anything Model (SAM) 2 has demonstrated remarkable foundational competence in semantic segmentation, with its memory mechanism and mask decoder further addressing challenges in video tracking and object occlusion, thereby achieving superior results in interactive segmentation for both images and videos.
The Llama 3 Herd of Models
This paper presents a new set of foundation models, called Llama 3.
Ranked #3 on
Multi-task Language Understanding
on MMLU
Dual-stage Hyperspectral Image Classification Model with Spectral Supertoken
Hyperspectral image classification, a task that assigns pre-defined classes to each pixel in a hyperspectral image of remote sensing scenes, often faces challenges due to the neglect of correlations between spectrally similar pixels.
Foundations and Frontiers of Graph Learning Theory
Recent advancements in graph learning have revolutionized the way to understand and analyze data with complex structures.
Benchmarking End-To-End Performance of AI-Based Chip Placement Algorithms
We executed six state-of-the-art AI-based chip placement algorithms on these designs and plugged the results of each single-point algorithm into the physical implementation workflow to obtain the final PPA results.
Revisiting Interpolation Augmentation for Speech-to-Text Generation
Speech-to-text (S2T) generation systems frequently face challenges in low-resource scenarios, primarily due to the lack of extensive labeled datasets.
LLM-Oracle Machines
Contemporary AI applications leverage large language models (LLMs) to harness their knowledge and reasoning abilities for natural language processing tasks.
Deep Symbolic Optimization for Combinatorial Optimization: Accelerating Node Selection by Discovering Potential Heuristics
With data-driven approaches, Dso4NS guides the search for mathematical expressions within the high-dimensional discrete symbolic space and then incorporates the highest-performing mathematical expressions into a solver.
Hire: Hybrid-modal Interaction with Multiple Relational Enhancements for Image-Text Matching
In this paper, we propose a Hybrid-modal Interaction with multiple Relational Enhancements (termed \textit{Hire}) for image-text matching, which correlates the intra- and inter-modal semantics between objects and words with implicit and explicit relationship modelling.
CodeR: Issue Resolving with Multi-Agent and Task Graphs
GitHub issue resolving recently has attracted significant attention from academia and industry.
Ranked #1 on
Bug fixing
on SWE-bench-lite
Reliability for Nerve Fiber Layer Reflectance Using Spectral Domain Optical Coherence Tomography
The clinical dataset selected 22 normal and 55 glaucoma eyes with at least two visits form functional and structural OCT (FSOCT) study.
FUSU: A Multi-temporal-source Land Use Change Segmentation Dataset for Fine-grained Urban Semantic Understanding
Although there have been advances in high-quality land cover datasets that reveal the physical features of urban landscapes, the lack of fine-grained land use datasets hinders a deeper understanding of how human activities are distributed across the landscape and the impact of these activities on the environment, thus constraining proper technique development.
Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances
Optimal transport has been very successful for various machine learning tasks; however, it is known to suffer from the curse of dimensionality.
Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space
Many studies use adversarial learning to generate perturbation during training process to model the discrepancy and improve the robustness of DRL.
DF-SLAM: Dictionary Factors Representation for High-Fidelity Neural Implicit Dense Visual SLAM System
Compared to neural implicit dense visual SLAM methods that directly encode scene information as features, our method exhibits superior scene detail reconstruction capabilities and more efficient memory usage, while our model size is insensitive to the size of the scene map, making our method more suitable for large-scale scenes.
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting
In this paper, we propose a novel visual Semantic-Spatial Self-Highlighting Network (termed 3SHNet) for high-precision, high-efficiency and high-generalization image-sentence retrieval.
Ranked #1 on
Cross-Modal Retrieval
on MSCOCO
Learning to Cut via Hierarchical Sequence/Set Model for Efficient Mixed-Integer Programming
Moreover, we observe that (P3) what order of selected cuts to prefer significantly impacts the efficiency of MILP solvers as well.
Length Generalization of Causal Transformers without Position Encoding
Generalizing to longer sentences is important for recent Transformer-based language models.
Trustworthy Multimodal Fusion for Sentiment Analysis in Ordinal Sentiment Space
To address the aforementioned problems, we propose a trustworthy multimodal sentiment ordinal network (TMSON) to improve performance in sentiment analysis.
A Survey of Neural Network Robustness Assessment in Image Recognition
We investigate the perturbation metrics and range representations used to measure the degree of perturbations on images, as well as the robustness metrics specifically for the robustness conditions of classification models.
Chaos in Motion: Unveiling Robustness in Remote Heart Rate Measurement through Brain-Inspired Skin Tracking
To address these issues, we regard the remote heart rate measurement as the process of analyzing the spatiotemporal characteristics of the optical flow signal in the video.
Enhancing Safety in Mixed Traffic: Learning-Based Modeling and Efficient Control of Autonomous and Human-Driven Vehicles
By incorporating a sparse GP technique in HV modeling and adopting a dynamic GP prediction within the MPC framework, we significantly reduced the computation time of GP-MPC, marking it only 4. 6% higher than that of the conventional MPC.
ROPO: Robust Preference Optimization for Large Language Models
Preference alignment is pivotal for empowering large language models (LLMs) to generate helpful and harmless responses.
IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation with Decoupled PEFT
This is also a notable improvement over the Adapter and LoRA, which require 37-39 GB GPU memory and 350-380 seconds per epoch for training.
A Tutorial on Gaussian Process Learning-based Model Predictive Control
This tutorial provides a systematic introduction to Gaussian process learning-based model predictive control (GP-MPC), an advanced approach integrating Gaussian process (GP) with model predictive control (MPC) for enhanced control in complex systems.
Reinforcement Learning-based Recommender Systems with Large Language Models for State Reward and Action Modeling
The LE is learned from a subset of user-item interaction data, thus reducing the need for large training data, and can synthesise user feedback for offline data by: (i) acting as a state model that produces high quality states that enrich the user representation, and (ii) functioning as a reward model to accurately capture nuanced user preferences on actions.
Non-Convex Robust Hypothesis Testing using Sinkhorn Uncertainty Sets
We present a new framework to address the non-convex robust hypothesis testing problem, wherein the goal is to seek the optimal detector that minimizes the maximum of worst-case type-I and type-II risk functions.
PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design
Retrieval-augmented generation (RAG) can enhance the generation quality of large language models (LLMs) by incorporating external token databases.
OSSAR: Towards Open-Set Surgical Activity Recognition in Robot-assisted Surgery
Existing algorithms dedicated to surgical activity recognition predominantly cater to pre-defined closed-set paradigms, ignoring the challenges of real-world open-set scenarios.
Accelerating PDE Data Generation via Differential Operator Action in Solution Space
It applies differential operators on these solutions, a process we call 'operator action', to efficiently generate precise PDE data points.
Learning to Stop Cut Generation for Efficient Mixed-Integer Linear Programming
A key problem for cuts is when to stop cuts generation, which is important for the efficiency of solving MILPs.
PointGL: A Simple Global-Local Framework for Efficient Point Cloud Analysis
Efficient analysis of point clouds holds paramount significance in real-world 3D applications.
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.
Machine Learning Insides OptVerse AI Solver: Design Principles and Applications
To this end, we present a comprehensive study on the integration of machine learning (ML) techniques into Huawei Cloud's OptVerse AI Solver, which aims to mitigate the scarcity of real-world mathematical programming instances, and to surpass the capabilities of traditional optimization techniques.
On Completeness of SDP-Based Barrier Certificate Synthesis over Unbounded Domains
Furthermore, motivated by this formulation, we introduce the definition of homogenized systems and propose a complete characterization of a family of non-polynomial barrier certificates with more expressive power.
FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited Knowledge
Despite the initial success of current audio backdoor attacks, they suffer from the following limitations: (i) Most of them require sufficient knowledge, which limits their widespread adoption.
Building Open-Ended Embodied Agent via Language-Policy Bidirectional Adaptation
Building embodied agents on integrating Large Language Models (LLMs) and Reinforcement Learning (RL) have revolutionized human-AI interaction: researchers can now leverage language instructions to plan decision-making for open-ended tasks.
GaussianHead: High-fidelity Head Avatars with Learnable Gaussian Derivation
Constructing vivid 3D head avatars for given subjects and realizing a series of animations on them is valuable yet challenging.
Content Significance Distribution of Sub-Text Blocks in Articles and Its Application to Article-Organization Assessment
We explore how to capture the significance of a sub-text block in an article and how it may be used for text mining tasks.
Affective Video Content Analysis: Decade Review and New Perspectives
In this study, we comprehensively review the development of AVCA over the past decade, particularly focusing on the most advanced methods adopted to address the three major challenges of video feature extraction, expression subjectivity, and multimodal feature fusion.
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).
Channel Estimation via Loss Field: Accurate Site-Trained Modeling for Shadowing Prediction
We propose a new channel model, CELF, which uses channel loss measurements from a deployed network in the area and a Bayesian linear regression method to estimate a site-specific loss field for the area.
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.
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.
Serving Deep Learning Model in Relational Databases
Serving deep learning (DL) models on relational data has become a critical requirement across diverse commercial and scientific domains, sparking growing interest recently.
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).
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
Can Class-Priors Help Single-Positive Multi-Label Learning?
Single-positive multi-label learning (SPMLL) is a typical weakly supervised multi-label learning problem, where each training example is annotated with only one positive label.
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.
Sample-adaptive Augmentation for Point Cloud Recognition Against Real-world Corruptions
Robust 3D perception under corruption has become an essential task for the realm of 3D vision.
A Ground Segmentation Method Based on Point Cloud Map for Unstructured Roads
Unstructured road scenes represented by open-pit mines have irregular boundary lines and uneven road surfaces, which lead to segmentation errors in current ground segmentation methods.
NineRec: A Benchmark Dataset Suite for Evaluating Transferable Recommendation
The development of TransRec has encountered multiple challenges, among which the lack of large-scale, high-quality transfer learning recommendation dataset and benchmark suites is one of the biggest obstacles.
Context-Aware Prompt Tuning for Vision-Language Model with Dual-Alignment
To achieve this, we introduce a pre-trained LLM to generate context descriptions, and we encourage the prompts to learn from the LLM's knowledge by alignment, as well as the alignment between prompts and local image features.
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.
A Novel Ehanced Move Recognition Algorithm Based on Pre-trained Models with Positional Embeddings
The recognition of abstracts is crucial for effectively locating the content and clarifying the article.
HiREN: Towards Higher Supervision Quality for Better Scene Text Image Super-Resolution
Observing the quality issue of HR images, in this paper we propose a novel idea to boost STISR by first enhancing the quality of HR images and then using the enhanced HR images as supervision to do STISR.
Community Detection Graph Convolutional Network for Overlap-Aware Speaker Diarization
The CDGCN-based clustering method consists of graph generation, sub-graph detection, and Graph-based Overlapped Speech Detection (Graph-OSD).
TrustGuard: GNN-based Robust and Explainable Trust Evaluation with Dynamicity Support
Among them, the spatial aggregation layer adopts a defense mechanism to robustly aggregate local trust, and the temporal aggregation layer applies an attention mechanism for effective learning of temporal patterns.
Can LLMs like GPT-4 outperform traditional AI tools in dementia diagnosis? Maybe, but not today
In this paper, we explore the potential of LLMs such as GPT-4 to outperform traditional AI tools in dementia diagnosis.
Exploring Adapter-based Transfer Learning for Recommender Systems: Empirical Studies and Practical Insights
If yes, we benchmark these existing adapters, which have been shown to be effective in NLP and CV tasks, in item recommendation tasks.
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.
RAF: Holistic Compilation for Deep Learning Model Training
In this paper, we present RAF, a deep learning compiler for training.
Sparse Bayesian Learning-Based 3D Spectrum Environment Map Construction-Sampling Optimization, Scenario-Dependent Dictionary Construction and Sparse Recovery
Then, a maximum and minimum distance (MMD) clustering-based SBL algorithm is proposed to recover the spectrum data at the unsampled positions and construct the whole 3D SEM.
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.
Variable Selection for Kernel Two-Sample Tests
We consider the variable selection problem for two-sample tests, aiming to select the most informative variables to distinguish samples from two groups.
Robust Representation Learning by Clustering with Bisimulation Metrics for Visual Reinforcement Learning with Distractions
To tackle this problem, we propose a novel clustering-based approach, namely Clustering with Bisimulation Metrics (CBM), which learns robust representations by grouping visual observations in the latent space.
LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergence
The key idea of LMC is to retrieve the discarded messages in backward passes based on a message passing formulation of backward passes.
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.
Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text Retrieval
Vision-language alignment learning for video-text retrieval arouses a lot of attention in recent years.
Deep learning numerical methods for high-dimensional fully nonlinear PIDEs and coupled FBSDEs with jumps
We propose a deep learning algorithm for solving high-dimensional parabolic integro-differential equations (PIDEs) and high-dimensional forward-backward stochastic differential equations with jumps (FBSDEJs), where the jump-diffusion process are derived by a Brownian motion and an independent compensated Poisson random measure.
Two Measure is Two Know: Calibration-free Full Duplex Monitoring for Software Radio Platforms
FDMonitor thus uses a bidirectional coupler, a two-channel receiver, and a new source separation algorithm to simultaneously estimate the transmitted signal and the signal incident on the antenna.
Efficient Exploration in Resource-Restricted Reinforcement Learning
In many real-world applications of reinforcement learning (RL), performing actions requires consuming certain types of resources that are non-replenishable in each episode.
Interpretable Diabetic Retinopathy Diagnosis based on Biomarker Activation Map
To ensure that the BAM only highlights classifier-utilized biomarkers an assistant generator was trained to do the opposite, producing scans that would be classified as referable by the classifier from non-referable scans.
SportsTrack: An Innovative Method for Tracking Athletes in Sports Scenes
The SportsMOT dataset aims to solve multiple object tracking of athletes in different sports scenes such as basketball or soccer.
LMD: A Learnable Mask Network to Detect Adversarial Examples for Speaker Verification
It utilizes score variation as an indicator to detect adversarial examples, where the score variation is the absolute discrepancy between the ASV scores of an original audio recording and its transformed audio synthesized from its masked complex spectrogram.
WeKws: A production first small-footprint end-to-end Keyword Spotting Toolkit
Keyword spotting (KWS) enables speech-based user interaction and gradually becomes an indispensable component of smart devices.
Tag-Set-Sequence Learning for Generating Question-Answer Pairs
Transformer-based QG models can generate question-answer pairs (QAPs) with high qualities, but may also generate silly questions for certain texts.
Spatial-aware Speaker Diarization for Multi-channel Multi-party Meeting
This paper describes a spatial-aware speaker diarization system for the multi-channel multi-party meeting.
FusionRCNN: LiDAR-Camera Fusion for Two-stage 3D Object Detection
Existing 3D detectors significantly improve the accuracy by adopting a two-stage paradigm which merely relies on LiDAR point clouds for 3D proposal refinement.
Contrastive Semantic-Guided Image Smoothing Network
Image smoothing is a fundamental low-level vision task that aims to preserve salient structures of an image while removing insignificant details.
Sparse Polynomial Optimization: Theory and Practice
Fortunately, for many applications, we can look at the problem in the eyes and exploit the inherent data structure arising from the cost and constraints describing the problem, for instance sparsity or symmetries.
Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion
One-shot voice conversion (VC) with only a single target speaker's speech for reference has become a hot research topic.
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.
Improving Pseudo Labels With Intra-Class Similarity for Unsupervised Domain Adaptation
In this paper, we propose a novel approach to improve the accuracy of the pseudo labels in the target domain.
Flow Rate Independent Multiscale Liquid Biopsy for Precision Oncology
Immunoaffinity-based liquid biopsies of circulating tumor cells (CTCs) hold great promise for cancer management, but typically suffer from low throughput, relative complexity and post-processing limitations.
FlowX: Towards Explainable Graph Neural Networks via Message Flows
We investigate the explainability of graph neural networks (GNNs) as a step toward elucidating their working mechanisms.
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.
TransRec: Learning Transferable Recommendation from Mixture-of-Modality Feedback
That is, the users and the interacted items are represented by their unique IDs, which are generally not shareable across different systems or platforms.
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.
Downstream Transformer Generation of Question-Answer Pairs with Preprocessing and Postprocessing Pipelines
We present a system called TP3 to perform a downstream task of transformers on generating question-answer pairs (QAPs) from a given article.
A Manifold Two-Sample Test Study: Integral Probability Metric with Neural Networks
Based on the approximation theory of neural networks, we show that the neural network IPM test has the type-II risk in the order of $n^{-(s+\beta)/d}$, which is in the same order of the type-II risk as the H\"older IPM test.
C3-STISR: Scene Text Image Super-resolution with Triple Clues
In this paper, we present a novel method C3-STISR that jointly exploits the recognizer's feedback, visual and linguistical information as clues to guide super-resolution.
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).
Contextual Networks and Unsupervised Ranking of Sentences
We construct a contextual network to represent a document with syntactic and semantic relations between word-sentence pairs, based on which we devise an unsupervised algorithm called CNATAR (Contextual Network And Text Analysis Rank) to score sentences, and rank them through a bi-objective 0-1 knapsack maximization problem over topic analysis and sentence scores.
Boilerplate Detection via Semantic Classification of TextBlocks
We present a hierarchical neural network model called SemText to detect HTML boilerplate based on a novel semantic representation of HTML tags, class names, and text blocks.
An Efficient End-to-End 3D Voxel Reconstruction based on Neural Architecture Search
However, many previous works employ neural networks with fixed architecture and size to represent different 3D objects, which lead to excessive network parameters for simple objects and limited reconstruction accuracy for complex objects.
A Survey of Neural Trojan Attacks and Defenses in Deep Learning
It provides a comprehensible gateway to the broader community to understand the recent developments in Neural Trojans.
The xmuspeech system for multi-channel multi-party meeting transcription challenge
By performing DMSNet based OSD module, the DER of cluster-based diarization system decrease significantly form 13. 44% to 7. 63%.
A Data-Driven Approach to Robust Hypothesis Testing Using Sinkhorn Uncertainty Sets
Hypothesis testing for small-sample scenarios is a practically important problem.
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.
Fooling the Eyes of Autonomous Vehicles: Robust Physical Adversarial Examples Against Traffic Sign Recognition Systems
From the view of object detectors, the traffic sign`s position and quality of the video are continuously changing, rendering the digital AEs ineffective in the physical world.
An Improved Reinforcement Learning Algorithm for Learning to Branch
Similar to offline reinforcement learning, we initially train on the demonstration data to accelerate learning massively.
Learning to Reformulate for Linear Programming
In the past decades, a serial of traditional operation research algorithms have been proposed to obtain the optimum of a given LP in a fewer solving time.
Learning Robust Policy against Disturbance in Transition Dynamics via State-Conservative Policy Optimization
Many existing algorithms learn robust policies by modeling the disturbance and applying it to source environments during training, which usually requires prior knowledge about the disturbance and control of simulators.
PAPooling: Graph-based Position Adaptive Aggregation of Local Geometry in Point Clouds
Fine-grained geometry, captured by aggregation of point features in local regions, is crucial for object recognition and scene understanding in point clouds.
Jointly Learning Agent and Lane Information for Multimodal Trajectory Prediction
JAL-MTP use a Social to Lane (S2L) module to jointly represent the static lane and the dynamic motion of the neighboring agents as instance-level lane, a Recurrent Lane Attention (RLA) mechanism for utilizing the instance-level lanes to predict the map-adaptive future trajectories and two selectors to identify the typical and reasonable trajectories.
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.
Multi-Modal Multi-Instance Learning for Retinal Disease Recognition
We propose in this paper Multi-Modal Multi-Instance Learning (MM-MIL) for selectively fusing CFP and OCT modalities.
Sinkhorn Distributionally Robust Optimization
We study distributionally robust optimization (DRO) with Sinkhorn distance -- a variant of Wasserstein distance based on entropic regularization.
XMUSPEECH System for VoxCeleb Speaker Recognition Challenge 2021
This paper describes the XMUSPEECH speaker recognition and diarisation systems for the VoxCeleb Speaker Recognition Challenge 2021.
A 60-GHz Radar Sensor for Micron-Scale Motion Detection
A compact, continuous-wave, mmWave radar sensor is developed for non-contact detection of micron-scale motions.
Technical Report of Team GraphMIRAcles in the WikiKG90M-LSC Track of OGB-LSC @ KDD Cup 2021
To address this challenge, we propose a framework that integrates three components -- a basic model ComplEx-CMRC, a rule miner AMIE 3, and an inference model to predict missing links.
Learning to Optimize Industry-Scale Dynamic Pickup and Delivery Problems
Our method is entirely data driven and thus adaptive, i. e., the relational representation of adjacent vehicles can be learned and corrected by ST-DDGN from data periodically.
Unsupervised Domain Expansion for Visual Categorization
In this paper we extend UDA by proposing a new task called unsupervised domain expansion (UDE), which aims to adapt a deep model for the target domain with its unlabeled data, meanwhile maintaining the model's performance on the source domain.
Ranked #1 on
Unsupervised Domain Expansion
on UDE-DomainNet
Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking
In video object tracking, there exist rich temporal contexts among successive frames, which have been largely overlooked in existing trackers.
Ranked #8 on
Object Tracking
on COESOT
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.
Analysing Wideband Absorbance Immittance in Normal and Ears with Otitis Media with Effusion Using Machine Learning
Wideband Absorbance Immittance (WAI) has been available for more than a decade, however its clinical use still faces the challenges of limited understanding and poor interpretation of WAI results.
On Explainability of Graph Neural Networks via Subgraph Explorations
To make the tree search more effective, we propose to use Shapley values as a measure of subgraph importance, which can also capture the interactions among different subgraphs.
Adversarially learning disentangled speech representations for robust multi-factor voice conversion
To increase the robustness of highly controllable style transfer on multiple factors in VC, we propose a disentangled speech representation learning framework based on adversarial learning.
UNIT: Unifying Tensorized Instruction Compilation
However, it is hard to leverage mixed precision without hardware support because of the overhead of data casting.
PICA: A Pixel Correlation-based Attentional Black-box Adversarial Attack
The studies on black-box adversarial attacks have become increasingly prevalent due to the intractable acquisition of the structural knowledge of deep neural networks (DNNs).
Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization
In this paper, we propose an attention-guided black-box adversarial attack based on the large-scale multiobjective evolutionary optimization, termed as LMOA.
The simpler the better: vanilla sgd revisited
The stochastic gradient descent (SGD) method, first proposed in 1950's, has been the foundation for deep-neural-network (DNN) training with numerous enhancements including adding a momentum or adaptively selecting learning rates, or using both strategies and more.
Topological charge engineering in lasing bound states in continuum
We experimentally analyze all four observed lasing BICs by imaging their far-field polarization vortices and their associated topological charges.
Optics
Deep Deterministic Policy Gradient for Relay Selection and Power Allocation in Cooperative Communication Network
Perfect channel state information (CSI) is usually required when considering relay selection and power allocation in cooperative communication.
Information Theory Systems and Control Systems and Control Information Theory
Promoting Stochasticity for Expressive Policies via a Simple and Efficient Regularization Method
However, in continuous action spaces, integrating entropy regularization with expressive policies is challenging and usually requires complex inference procedures.