Search Results for author:
Found 45 papers, 16 papers with code
dFLMoE: Decentralized Federated Learning via Mixture of Experts for Medical Data Analysis
This centralized approach would integrate the knowledge from each client into a centralized server, and the knowledge would be already undermined during the centralized integration before it reaches back to each client.
MMARD: Improving the Min-Max Optimization Process in Adversarial Robustness Distillation
The ARD can be summarized as a min-max optimization process, i. e., synthesizing adversarial examples (inner) & training the student (outer).
VideoPure: Diffusion-based Adversarial Purification for Video Recognition
Given an adversarial example, we first employ temporal DDIM inversion to transform the input distribution into a temporally consistent and trajectory-defined distribution, covering adversarial noise while preserving more video structure.
Pruning for Sparse Diffusion Models based on Gradient Flow
Diffusion Models (DMs) have impressive capabilities among generation models, but are limited to slower inference speeds and higher computational costs.
Boosting Adversarial Transferability with Spatial Adversarial Alignment
To achieve high transferability, we propose a technique termed Spatial Adversarial Alignment (SAA), which employs an alignment loss and leverages a witness model to fine-tune the surrogate model.
MedAide: Towards an Omni Medical Aide via Specialized LLM-based Multi-Agent Collaboration
Large Language Model (LLM)-driven interactive systems currently show potential promise in healthcare domains.
X-Prompt: Multi-modal Visual Prompt for Video Object Segmentation
The X-Prompt framework first pre-trains a video object segmentation foundation model using RGB data, and then utilize the additional modality of the prompt to adapt it to downstream multi-modal tasks with limited data.
General Compression Framework for Efficient Transformer Object Tracking
Thus, we propose a general model compression framework for efficient transformer object tracking, named CompressTracker, to reduce the size of a pre-trained tracking model into a lightweight tracker with minimal performance degradation.
KAN-HyperpointNet for Point Cloud Sequence-Based 3D Human Action Recognition
In addition, we present a D-Hyperpoint KANsMixer module, which is recursively applied to nested groupings of D-Hyperpoints to learn the action discrimination information and creatively integrates Kolmogorov-Arnold Networks (KAN) to enhance spatio-temporal interaction within D-Hyperpoints.
TagOOD: A Novel Approach to Out-of-Distribution Detection via Vision-Language Representations and Class Center Learning
We conduct extensive experiments to evaluate TagOOD on several benchmark datasets and demonstrate its superior performance compared to existing OOD detection methods.
Improving Factuality in Large Language Models via Decoding-Time Hallucinatory and Truthful Comparators
In this paper, we propose a Comparator-driven Decoding-Time (CDT) framework to alleviate the response hallucination.
Improving Adversarial Transferability with Neighbourhood Gradient Information
Leveraging this, we propose the NGI-Attack, which incorporates Example Backtracking and Multiplex Mask strategies, to use this gradient information and enhance transferability fully.
PG-Attack: A Precision-Guided Adversarial Attack Framework Against Vision Foundation Models for Autonomous Driving
Additionally, we won First-Place in the CVPR 2024 Workshop Challenge: Black-box Adversarial Attacks on Vision Foundation Models and codes are available at https://github. com/fuhaha824/PG-Attack.
Large Vision-Language Models as Emotion Recognizers in Context Awareness
Extensive experiments and analyses demonstrate that LVLMs achieve competitive performance in the CAER task across different paradigms.
Towards Context-Aware Emotion Recognition Debiasing from a Causal Demystification Perspective via De-confounded Training
To address the issue, we embrace causal inference to disentangle the models from the impact of such bias, and formulate the causalities among variables in the CAER task via a customized causal graph.
Self-Cooperation Knowledge Distillation for Novel Class Discovery
Existing works focus on instance-level or class-level knowledge representation and build a shared representation space to achieve performance improvements.
LVOS: A Benchmark for Large-scale Long-term Video Object Segmentation
Video object segmentation (VOS) aims to distinguish and track target objects in a video.
De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts
Data-Free Knowledge Distillation (DFKD) is a promising task to train high-performance small models to enhance actual deployment without relying on the original training data.
Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction
Existing work rarely studies the transferability of attacks on VLP models, resulting in a substantial performance gap from white-box attacks.
OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning
To evaluate the effectiveness of our general framework OneTracker, which is consisted of Foundation Tracker and Prompt Tracker, we conduct extensive experiments on 6 popular tracking tasks across 11 benchmarks and our OneTracker outperforms other models and achieves state-of-the-art performance.
Ranked #26 on
Rgb-T Tracking
on RGBT234
ClickVOS: Click Video Object Segmentation
To address these limitations, we propose the setting named Click Video Object Segmentation (ClickVOS) which segments objects of interest across the whole video according to a single click per object in the first frame.
Towards Multimodal Sentiment Analysis Debiasing via Bias Purification
In the inference phase, given a factual multimodal input, MCIS imagines two counterfactual scenarios to purify and mitigate these biases.
Debiased Multimodal Understanding for Human Language Sequences
Human multimodal language understanding (MLU) is an indispensable component of expression analysis (e. g., sentiment or humor) from heterogeneous modalities, including visual postures, linguistic contents, and acoustic behaviours.
Delving into Decision-based Black-box Attacks on Semantic Segmentation
We conduct adversarial robustness evaluation on 5 models from Cityscapes and ADE20K under 8 attacks.
Exploring Decision-based Black-box Attacks on Face Forgery Detection
Further, the fake faces by our method can pass face forgery detection and face recognition, which exposes the security problems of face forgery detectors.
FECFusion: Infrared and visible image fusion network based on fast edge convolution
The purpose of infrared and visible image fusion is to integrate the complementary information from heterogeneous images in order to enhance their detailed scene information.
Improving Generalization in Visual Reinforcement Learning via Conflict-aware Gradient Agreement Augmentation
In particular, CG2A develops a Gradient Agreement Solver to adaptively balance the varying gradient magnitudes, and introduces a Soft Gradient Surgery strategy to alleviate the gradient conflicts.
Sampling to Distill: Knowledge Transfer from Open-World Data
Data-Free Knowledge Distillation (DFKD) is a novel task that aims to train high-performance student models using only the pre-trained teacher network without original training data.
AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception
Driver distraction has become a significant cause of severe traffic accidents over the past decade.
Query-Efficient Decision-based Black-Box Patch Attack
In this work, we first explore the decision-based patch attack.
OpenVIS: Open-vocabulary Video Instance Segmentation
Furthermore, to prevent the tracking module from being constrained by the training data with limited categories, we propose the universal rollout association, which transforms the tracking problem into predicting the next frame's instance tracking token.
Non-rigid Point Cloud Registration for Middle Ear Diagnostics with Endoscopic Optical Coherence Tomography
To overcome the lack of labeled training data, a fast and effective generation pipeline in Blender3D is designed to simulate middle ear shapes and extract in-vivo noisy and partial point clouds.
Out of Thin Air: Exploring Data-Free Adversarial Robustness Distillation
Adversarial Robustness Distillation (ARD) is a promising task to solve the issue of limited adversarial robustness of small capacity models while optimizing the expensive computational costs of Adversarial Training (AT).
Efficient Decision-based Black-box Patch Attacks on Video Recognition
First, STDE introduces target videos as patch textures and only adds patches on keyframes that are adaptively selected by temporal difference.
Context De-confounded Emotion Recognition
However, a long-overlooked issue is that a context bias in existing datasets leads to a significantly unbalanced distribution of emotional states among different context scenarios.
Explicit and Implicit Knowledge Distillation via Unlabeled Data
Data-free knowledge distillation is a challenging model lightweight task for scenarios in which the original dataset is not available.
Adversarial Contrastive Distillation with Adaptive Denoising
To this end, we propose a novel structured ARD method called Contrastive Relationship DeNoise Distillation (CRDND).
Boosting the Transferability of Adversarial Attacks with Global Momentum Initialization
Particularly, when attacking advanced defense methods in the image domain, it achieves an average attack success rate of 95. 4%.
LVOS: A Benchmark for Long-term Video Object Segmentation
The videos in our LVOS last 1. 59 minutes on average, which is 20 times longer than videos in existing VOS datasets.
Shape Matters: Deformable Patch Attack
Though deep neural networks (DNNs) have demonstrated excellent performance in computer vision, they are susceptible and vulnerable to carefully crafted adversarial examples which can mislead DNNs to incorrect outputs.
DPCNet: Dual Path Multi-Excitation Collaborative Network for Facial Expression Representation Learning in Videos
To obtain consistent prediction probabilities from the dual path, we further propose a dual path regularization loss, aiming to minimize the divergence between the distributions of two-path embeddings.
Ranked #18 on
Dynamic Facial Expression Recognition
on DFEW
Dynamic Facial Expression Recognition
Representation Learning
Towards Practical Certifiable Patch Defense with Vision Transformer
To move towards a practical certifiable patch defense, we introduce Vision Transformer (ViT) into the framework of Derandomized Smoothing (DS).
Efficient universal shuffle attack for visual object tracking
Recently, adversarial attacks have been applied in visual object tracking to deceive deep trackers by injecting imperceptible perturbations into video frames.
CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakes
Then, we design a two-level perturbation fusion strategy to alleviate the conflict between the adversarial watermarks generated by different facial images and models.
RPATTACK: Refined Patch Attack on General Object Detectors
Firstly, we propose a patch selection and refining scheme to find the pixels which have the greatest importance for attack and remove the inconsequential perturbations gradually.
