Copertina

Towards Robust Semantic Segmentation against Patch-based Attack via Attention Refinement

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yuan, Zheng, Zhang, Jie, Wang, Yude, Shan, Shiguang, Chen, Xilin
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

FullLoRA: Efficiently Boosting the Robustness of Pretrained Vision Transformers
di: Yuan, Zheng, et al.
Pubblicazione: (2024)

EntropyScan: Towards Model-level Backdoor Detection in LVLMs via Visual Attention Entropy
di: Ge, Xuanyu, et al.
Pubblicazione: (2026)

Trigger without Trace: Towards Stealthy Backdoor Attack on Text-to-Image Diffusion Models
di: Zhang, Jie, et al.
Pubblicazione: (2025)

Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models
di: Wang, Zhongqi, et al.
Pubblicazione: (2025)

Image to Pseudo-Episode: Boosting Few-Shot Segmentation by Unlabeled Data
di: Zhang, Jie, et al.
Pubblicazione: (2024)

Semantic or Covariate? A Study on the Intractable Case of Out-of-Distribution Detection
di: Long, Xingming, et al.
Pubblicazione: (2024)

T2VAttack: Adversarial Attack on Text-to-Video Diffusion Models
di: Li, Changzhen, et al.
Pubblicazione: (2025)

What Makes VLMs Robust? Towards Reconciling Robustness and Accuracy in Vision-Language Models
di: Nie, Sen, et al.
Pubblicazione: (2026)

V-Attack: Targeting Disentangled Value Features for Controllable Adversarial Attacks on LVLMs
di: Nie, Sen, et al.
Pubblicazione: (2025)

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP
di: Nie, Sen, et al.
Pubblicazione: (2026)

T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models
di: Wang, Zhongqi, et al.
Pubblicazione: (2024)

Assimilation Matters: Model-level Backdoor Detection in Vision-Language Pretrained Models
di: Wang, Zhongqi, et al.
Pubblicazione: (2025)

Dual Attention Guided Defense Against Malicious Edits
di: Zhang, Jie, et al.
Pubblicazione: (2025)

GLip: A Global-Local Integrated Progressive Framework for Robust Visual Speech Recognition
di: Wang, Tianyue, et al.
Pubblicazione: (2025)

VOPE: Revisiting Hallucination of Vision-Language Models in Voluntary Imagination Task
di: Long, Xingming, et al.
Pubblicazione: (2025)

Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradox
di: Long, Xingming, et al.
Pubblicazione: (2024)

Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness
di: Wang, Sibo, et al.
Pubblicazione: (2024)

Measuring the Measurers: Quality Evaluation of Hallucination Benchmarks for Large Vision-Language Models
di: Yan, Bei, et al.
Pubblicazione: (2024)

ACT Now: Preempting LVLM Hallucinations via Adaptive Context Integration
di: Yan, Bei, et al.
Pubblicazione: (2026)

Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gating
di: Cao, Xiangkui, et al.
Pubblicazione: (2026)

Towards Transferable Defense Against Malicious Image Edits
di: Zhang, Jie, et al.
Pubblicazione: (2025)

Adaptive Perturbation for Adversarial Attack
di: Yuan, Zheng, et al.
Pubblicazione: (2021)

Dysca: A Dynamic and Scalable Benchmark for Evaluating Perception Ability of LVLMs
di: Zhang, Jie, et al.
Pubblicazione: (2024)

Semantic Mismatch and Perceptual Degradation: A New Perspective on Image Editing Immunity
di: Dong, Shuai, et al.
Pubblicazione: (2025)

HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attention
di: Tang, Xiaolong, et al.
Pubblicazione: (2024)

CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation
di: Xu, Yifeng, et al.
Pubblicazione: (2024)

VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model
di: Wang, Sibo, et al.
Pubblicazione: (2024)

MM-MoralBench: A MultiModal Moral Evaluation Benchmark for Large Vision-Language Models
di: Yan, Bei, et al.
Pubblicazione: (2024)

INFACT: A Diagnostic Benchmark for Induced Faithfulness and Factuality Hallucinations in Video-LLMs
di: Yang, Junqi, et al.
Pubblicazione: (2026)

REVAL: A Comprehension Evaluation on Reliability and Values of Large Vision-Language Models
di: Zhang, Jie, et al.
Pubblicazione: (2025)

Generalized Face Liveness Detection via De-fake Face Generator
di: Long, Xingming, et al.
Pubblicazione: (2024)

Component-Based Out-of-Distribution Detection
di: Liu, Wenrui, et al.
Pubblicazione: (2026)

EfficientMT: Efficient Temporal Adaptation for Motion Transfer in Text-to-Video Diffusion Models
di: Cai, Yufei, et al.
Pubblicazione: (2025)

Task-adaptive Q-Face
di: Sun, Haomiao, et al.
Pubblicazione: (2024)

un$^2$CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP
di: Li, Yinqi, et al.
Pubblicazione: (2025)

PAD: Patch-Agnostic Defense against Adversarial Patch Attacks
di: Jing, Lihua, et al.
Pubblicazione: (2024)

Steering Vision-Language Pre-trained Models for Incremental Face Presentation Attack Detection
di: Li, Haoze, et al.
Pubblicazione: (2025)

DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks
di: Li, Yinqi, et al.
Pubblicazione: (2025)

Anonymization Prompt Learning for Facial Privacy-Preserving Text-to-Image Generation
di: Shi, Liang, et al.
Pubblicazione: (2024)

Confidence Aware Learning for Reliable Face Anti-spoofing
di: Long, Xingming, et al.
Pubblicazione: (2024)