Copertina

Not Blind but Silenced: Rebalancing Vision and Language via Adversarial Counter-Commonsense Equilibrium

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xiao, Qingxin, Zhao, Peilin, Zhao, Yangyang, Dang, Lingwei, Wu, Qingyao
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Taming the Long Tail: Rebalancing Adversarial Training via Adaptive Perturbation
di: Zhang, Lilin, et al.
Pubblicazione: (2026)

Video Anomaly Detection with Semantics-Aware Information Bottleneck
di: Li, Juntong, et al.
Pubblicazione: (2025)

Long-Tailed Object Detection Pre-training: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction
di: Duan, Chen-Long, et al.
Pubblicazione: (2024)

Long-Tail Learning with Rebalanced Contrastive Loss
di: De Alvis, Charika, et al.
Pubblicazione: (2023)

ABC Easy as 123: A Blind Counter for Exemplar-Free Multi-Class Class-agnostic Counting
di: Hobley, Michael A., et al.
Pubblicazione: (2023)

Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model
di: Ma, Huan, et al.
Pubblicazione: (2024)

Improving Adversarial Transferability in MLLMs via Dynamic Vision-Language Alignment Attack
di: Gu, Chenhe, et al.
Pubblicazione: (2025)

Hessian Surgery: Class-Targeted Post-Hoc Rebalancing via Hessian Spike Perturbation
di: Vigna, Hugo, et al.
Pubblicazione: (2026)

Protego: Detecting Adversarial Examples for Vision Transformers via Intrinsic Capabilities
di: Wu, Jialin, et al.
Pubblicazione: (2025)

It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data
di: Schnaus, Dominik, et al.
Pubblicazione: (2025)

Vision Transformer-based Adversarial Domain Adaptation
di: Li, Yahan, et al.
Pubblicazione: (2024)

Data Selection for Fine-tuning Vision Language Models via Cross Modal Alignment Trajectories
di: Naharas, Nilay, et al.
Pubblicazione: (2025)

Transferable Adversarial Attacks on Black-Box Vision-Language Models
di: Hu, Kai, et al.
Pubblicazione: (2025)

Vision Language Models are Biased
di: Vo, An, et al.
Pubblicazione: (2025)

Self-Bootstrapping for Versatile Test-Time Adaptation
di: Niu, Shuaicheng, et al.
Pubblicazione: (2025)

Model-agnostic Adversarial Attack and Defense for Vision-Language-Action Models
di: Xu, Haochuan, et al.
Pubblicazione: (2025)

Large-Scale Riemannian Meta-Optimization via Subspace Adaptation
di: Yu, Peilin, et al.
Pubblicazione: (2025)

Attack Anything: Blind DNNs via Universal Background Adversarial Attack
di: Lian, Jiawei, et al.
Pubblicazione: (2024)

Mitigating Accuracy-Robustness Trade-off via Balanced Multi-Teacher Adversarial Distillation
di: Zhao, Shiji, et al.
Pubblicazione: (2023)

WriteViT: Handwritten Text Generation with Vision Transformer
di: Nam, Dang Hoai, et al.
Pubblicazione: (2025)

Evaluating the Adversarial Robustness of Detection Transformers
di: Nazeri, Amirhossein, et al.
Pubblicazione: (2024)

A Survey of Vision Transformers in Autonomous Driving: Current Trends and Future Directions
di: Lai-Dang, Quoc-Vinh
Pubblicazione: (2024)

Towards Fair Class-wise Robustness: Class Optimal Distribution Adversarial Training
di: Zhi, Hongxin, et al.
Pubblicazione: (2025)

Commonsense for Zero-Shot Natural Language Video Localization
di: Holla, Meghana, et al.
Pubblicazione: (2023)

A Wander Through the Multimodal Landscape: Efficient Transfer Learning via Low-rank Sequence Multimodal Adapter
di: Guo, Zirun, et al.
Pubblicazione: (2024)

SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios
di: Dang, Lingwei, et al.
Pubblicazione: (2025)

Continual Learning with Vision-Language Models via Semantic-Geometry Preservation
di: He, Chiyuan, et al.
Pubblicazione: (2026)

Do Vision-Language Transformers Exhibit Visual Commonsense? An Empirical Study of VCR
di: Li, Zhenyang, et al.
Pubblicazione: (2024)

Ramen: Robust Test-Time Adaptation of Vision-Language Models with Active Sample Selection
di: Bao, Wenxuan, et al.
Pubblicazione: (2026)

Light-weight Fine-tuning Method for Defending Adversarial Noise in Pre-trained Medical Vision-Language Models
di: Han, Xu, et al.
Pubblicazione: (2024)

Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation
di: Zhao, Shiji, et al.
Pubblicazione: (2023)

PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization
di: Chen, Zining, et al.
Pubblicazione: (2024)

One-Step Diffusion Distillation via Deep Equilibrium Models
di: Geng, Zhengyang, et al.
Pubblicazione: (2023)

Boosting Adversarial Transferability via Ensemble Non-Attention
di: Zou, Yipeng, et al.
Pubblicazione: (2025)

Ultrasound Vision-Language Alignment via Contrastive Learning
di: Lyu, Zhuoyang, et al.
Pubblicazione: (2026)

TRIX- Trading Adversarial Fairness via Mixed Adversarial Training
di: Medi, Tejaswini, et al.
Pubblicazione: (2025)

MirrorCheck: Efficient Adversarial Defense for Vision-Language Models
di: Fares, Samar, et al.
Pubblicazione: (2024)

PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction
di: Meng, Ziqiao, et al.
Pubblicazione: (2025)

SyncMV4D: Synchronized Multi-view Joint Diffusion of Appearance and Motion for Hand-Object Interaction Synthesis
di: Dang, Lingwei, et al.
Pubblicazione: (2025)

CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interaction
di: Choi, Suhwan, et al.
Pubblicazione: (2024)