Search Results for author:
Found 43 papers, 21 papers with code
Model-Editing-Based Jailbreak against Safety-aligned Large Language Models
Large Language Models (LLMs) have transformed numerous fields by enabling advanced natural language interactions but remain susceptible to critical vulnerabilities, particularly jailbreak attacks.
GlitchProber: Advancing Effective Detection and Mitigation of Glitch Tokens in Large Language Models
In this work, we aim to enhance the understanding of glitch tokens and propose techniques for their detection and mitigation.
DAC: 2D-3D Retrieval with Noisy Labels via Divide-and-Conquer Alignment and Correction
To tackle this problem, we propose a Divide-and-conquer 2D-3D cross-modal Alignment and Correction framework (DAC), which comprises Multimodal Dynamic Division (MDD) and Adaptive Alignment and Correction (AAC).
AdapNet: Adaptive Noise-Based Network for Low-Quality Image Retrieval
To mitigate this issue, we introduce a novel setting for low-quality image retrieval, and propose an Adaptive Noise-Based Network (AdapNet) to learn robust abstract representations.
Lockpicking LLMs: A Logit-Based Jailbreak Using Token-level Manipulation
Large language models (LLMs) have transformed the field of natural language processing, but they remain susceptible to jailbreaking attacks that exploit their capabilities to generate unintended and potentially harmful content.
Glitch Tokens in Large Language Models: Categorization Taxonomy and Effective Detection
We present categorizations of the identified glitch tokens and symptoms exhibited by LLMs when interacting with glitch tokens.
Memory Consistency Guided Divide-and-Conquer Learning for Generalized Category Discovery
Generalized category discovery (GCD) aims at addressing a more realistic and challenging setting of semi-supervised learning, where only part of the category labels are assigned to certain training samples.
Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection
Industrial anomaly detection is generally addressed as an unsupervised task that aims at locating defects with only normal training samples.
Collaborative Weakly Supervised Video Correlation Learning for Procedure-Aware Instructional Video Analysis
Our framework comprises two core modules: collaborative step mining and frame-to-step alignment.
Density Matters: Improved Core-set for Active Domain Adaptive Segmentation
Active domain adaptation has emerged as a solution to balance the expensive annotation cost and the performance of trained models in semantic segmentation.
Projective Parallel Single-Pixel Imaging: 3D Structured Light Scanning Under Global Illumination
The 4D LTC in pPSI are reduced to projection functions, thereby enabling a highly efficient data capture process.
Align, Perturb and Decouple: Toward Better Leverage of Difference Information for RSI Change Detection
In this paper, we revisit the importance of feature difference for change detection in RSI, and propose a series of operations to fully exploit the difference information: Alignment, Perturbation and Decoupling (APD).
Transavs: End-To-End Audio-Visual Segmentation With Transformer
Generally AVS faces two key challenges: (1) Audio signals inherently exhibit a high degree of information density, as sounds produced by multiple objects are entangled within the same audio stream; (2) Objects of the same category tend to produce similar audio signals, making it difficult to distinguish between them and thus leading to unclear segmentation results.
Few-shot Action Recognition via Intra- and Inter-Video Information Maximization
The alignment model performs temporal and spatial action alignment sequentially at the feature level, leading to more precise measurements of inter-video similarity.
Self-Supervised Likelihood Estimation with Energy Guidance for Anomaly Segmentation in Urban Scenes
Based on the proposed estimators, we devise an adaptive self-supervised training framework, which exploits the contextual reliance and estimated likelihood to refine mask annotations in anomaly areas.
Learning with Noisy labels via Self-supervised Adversarial Noisy Masking
Collecting large-scale datasets is crucial for training deep models, annotating the data, however, inevitably yields noisy labels, which poses challenges to deep learning algorithms.
Ranked #2 on
Image Classification
on Clothing1M
(using extra training data)
Learning from Noisy Labels with Decoupled Meta Label Purifier
Training deep neural networks(DNN) with noisy labels is challenging since DNN can easily memorize inaccurate labels, leading to poor generalization ability.
Rethinking the Metric in Few-shot Learning: From an Adaptive Multi-Distance Perspective
In this paper, for the first time, we investigate the contributions of different distance metrics, and propose an adaptive fusion scheme, bringing significant improvements in few-shot classification.
Learning from Noisy Labels with Coarse-to-Fine Sample Credibility Modeling
Specifically, for the clean set, we deliberately design a memory-based modulation scheme to dynamically adjust the contribution of each sample in terms of its historical credibility sequence during training, thus alleviating the effect from noisy samples incorrectly grouped into the clean set.
Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation
Unsupervised Domain Adaptation (UDA) aims to adapt the model trained on the labeled source domain to an unlabeled target domain.
Ranked #15 on
Unsupervised Domain Adaptation
on SYNTHIA-to-Cityscapes
Learning Distinctive Margin toward Active Domain Adaptation
Despite plenty of efforts focusing on improving the domain adaptation ability (DA) under unsupervised or few-shot semi-supervised settings, recently the solution of active learning started to attract more attention due to its suitability in transferring model in a more practical way with limited annotation resource on target data.
Reinforcement Learning in Practice: Opportunities and Challenges
This article is a gentle discussion about the field of reinforcement learning in practice, about opportunities and challenges, touching a broad range of topics, with perspectives and without technical details.
Exploring the Semi-supervised Video Object Segmentation Problem from a Cyclic Perspective
We conduct comprehensive comparison and detailed analysis on challenging benchmarks of DAVIS16, DAVIS17 and Youtube-VOS, demonstrating that the cyclic mechanism is helpful to enhance segmentation quality, improve the robustness of VOS systems, and further provide qualitative comparison and interpretation on how different VOS algorithms work.
LSTC: Boosting Atomic Action Detection with Long-Short-Term Context
We demonstrate that both temporal grains are beneficial to atomic action recognition.
Robust Learning with Adaptive Sample Credibility Modeling
For the clean set, we deliberately design a memory-based modulation scheme to dynamically adjust the contribution of each sample in terms of its historical credibility sequence during training, thus to alleviate the effect from potential hard noisy samples in clean set.
Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization
The crux of self-supervised video representation learning is to build general features from unlabeled videos.
TA2N: Two-Stage Action Alignment Network for Few-shot Action Recognition
The first stage locates the action by learning a temporal affine transform, which warps each video feature to its action duration while dismissing the action-irrelevant feature (e. g. background).
Variational Pedestrian Detection
Pedestrian detection in a crowd is a challenging task due to a high number of mutually-occluding human instances, which brings ambiguity and optimization difficulties to the current IoU-based ground truth assignment procedure in classical object detection methods.
Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation
In this paper, we address several inadequacies of current video object segmentation pipelines.
Finding Action Tubes with a Sparse-to-Dense Framework
The task of spatial-temporal action detection has attracted increasing attention among researchers.
Ranked #3 on
Action Detection
on UCF Sports
(Video-mAP 0.2 metric)
CFAD: Coarse-to-Fine Action Detector for Spatiotemporal Action Localization
Most current pipelines for spatio-temporal action localization connect frame-wise or clip-wise detection results to generate action proposals, where only local information is exploited and the efficiency is hindered by dense per-frame localization.
Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events
To this end, we present a new large-scale dataset with comprehensive annotations, named Human-in-Events or HiEve (Human-centric video analysis in complex Events), for the understanding of human motions, poses, and actions in a variety of realistic events, especially in crowd & complex events.
TRP: Trained Rank Pruning for Efficient Deep Neural Networks
The TRP trained network inherently has a low-rank structure, and is approximated with negligible performance loss, thus eliminating the fine-tuning process after low rank decomposition.
Trained Rank Pruning for Efficient Deep Neural Networks
To accelerate DNNs inference, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations.
Reinforcement Learning Applications
We start with a brief introduction to reinforcement learning (RL), about its successful stories, basics, an example, issues, the ICML 2019 Workshop on RL for Real Life, how to use it, study material and an outlook.
Annotation-Free Cardiac Vessel Segmentation via Knowledge Transfer from Retinal Images
Segmenting coronary arteries is challenging, as classic unsupervised methods fail to produce satisfactory results and modern supervised learning (deep learning) requires manual annotation which is often time-consuming and can some time be infeasible.
Group Re-Identification with Multi-grained Matching and Integration
The task of re-identifying groups of people underdifferent camera views is an important yet less-studied problem. Group re-identification (Re-ID) is a very challenging task sinceit is not only adversely affected by common issues in traditionalsingle object Re-ID problems such as viewpoint and human posevariations, but it also suffers from changes in group layout andgroup membership.
Trained Rank Pruning for Efficient Deep Neural Networks
We propose Trained Rank Pruning (TRP), which iterates low rank approximation and training.
Deep Reinforcement Learning
We start with background of artificial intelligence, machine learning, deep learning, and reinforcement learning (RL), with resources.
Network Decoupling: From Regular to Depthwise Separable Convolutions
Depthwise separable convolution has shown great efficiency in network design, but requires time-consuming training procedure with full training-set available.
Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages
Based on the deeply supervised object detection (DSOD) framework, we propose Tiny-DSOD dedicating to resource-restricted usages.
Deep Reinforcement Learning: An Overview
We start with background of machine learning, deep learning and reinforcement learning.
A General Projection Property for Distribution Families
We prove that linear projections between distribution families with fixed first and second moments are surjective, regardless of dimension.
