Imagen de Portada

Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ma, Huan, Zhu, Yan, Zhang, Changqing, Zhao, Peilin, Wu, Baoyuan, Huang, Long-Kai, Hu, Qinghua, Wu, Bingzhe
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning
por: Ma, Huan, et al.
Publicado: (2023)

VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models
por: Zhu, Zihao, et al.
Publicado: (2023)

EARBench: Towards Evaluating Physical Risk Awareness for Task Planning of Foundation Model-based Embodied AI Agents
por: Zhu, Zihao, et al.
Publicado: (2024)

Test-Time Model Adaptation with Only Forward Passes
por: Niu, Shuaicheng, et al.
Publicado: (2024)

DOTA: Distributional Test-Time Adaptation of Vision-Language Models
por: Han, Zongbo, et al.
Publicado: (2024)

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

Test-Time Dynamic Image Fusion
por: Cao, Bing, et al.
Publicado: (2024)

Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting
por: Tan, Mingkui, et al.
Publicado: (2024)

Probing the Safety Response Boundary of Large Language Models via Unsafe Decoding Path Generation
por: Wang, Haoyu, et al.
Publicado: (2024)

HMGIE: Hierarchical and Multi-Grained Inconsistency Evaluation for Vision-Language Data Cleansing
por: Zhu, Zihao, et al.
Publicado: (2024)

OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure
por: Shi, Chuancheng, et al.
Publicado: (2026)

Exploring Task-Level Optimal Prompts for Visual In-Context Learning
por: Zhu, Yan, et al.
Publicado: (2025)

Flatness Guided Test-Time Adaptation for Vision-Language Models
por: Li, Aodi, et al.
Publicado: (2025)

Federated Nested Learning: Collaborative Training of Self-Referential Memories for Test-Time Adaptation
por: Chen, Hong, et al.
Publicado: (2026)

Bayesian Test-Time Adaptation for Vision-Language Models
por: Zhou, Lihua, et al.
Publicado: (2025)

Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
por: Zhao, Shuai, et al.
Publicado: (2023)

Negation-Aware Test-Time Adaptation for Vision-Language Models
por: Han, Haochen, et al.
Publicado: (2025)

Prototype-Based Test-Time Adaptation of Vision-Language Models
por: Huang, Zhaohong, et al.
Publicado: (2026)

COME: Test-time adaption by Conservatively Minimizing Entropy
por: Zhang, Qingyang, et al.
Publicado: (2024)

SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning
por: Chen, Junkai, et al.
Publicado: (2025)

Class-Conditional Neural Polarizer: A Lightweight and Effective Backdoor Defense by Purifying Poisoned Features
por: Zhu, Mingli, et al.
Publicado: (2025)

Federated Low-Rank Adaptation for Foundation Models: A Survey
por: Yang, Yiyuan, et al.
Publicado: (2025)

Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization
por: Zhang, Qingyang, et al.
Publicado: (2025)

Realistic Test-Time Adaptation of Vision-Language Models
por: Zanella, Maxime, et al.
Publicado: (2025)

Noisy Test-Time Adaptation in Vision-Language Models
por: Cao, Chentao, et al.
Publicado: (2025)

Test-Time Adaptation for Tactile-Vision-Language Models
por: Ye, Chuyang, et al.
Publicado: (2026)

Efficient Test-Time Adaptation of Vision-Language Models
por: Karmanov, Adilbek, et al.
Publicado: (2024)

DeepEraser: Deep Iterative Context Mining for Generic Text Eraser
por: Feng, Hao, et al.
Publicado: (2024)

NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction
por: Wang, Qichao, et al.
Publicado: (2025)

Adapt in the Wild: Test-Time Entropy Minimization with Sharpness and Feature Regularization
por: Niu, Shuaicheng, et al.
Publicado: (2025)

Not Blind but Silenced: Rebalancing Vision and Language via Adversarial Counter-Commonsense Equilibrium
por: Xiao, Qingxin, et al.
Publicado: (2026)

FRET: Feature Redundancy Elimination for Test Time Adaptation
por: You, Linjing, et al.
Publicado: (2025)

Ultra-Light Test-Time Adaptation for Vision--Language Models
por: Kim, Byunghyun
Publicado: (2025)

Online Gaussian Test-Time Adaptation of Vision-Language Models
por: Fuchs, Clément, et al.
Publicado: (2025)

CLIPTTA: Robust Contrastive Vision-Language Test-Time Adaptation
por: Lafon, Marc, et al.
Publicado: (2025)

Frustratingly Easy Test-Time Adaptation of Vision-Language Models
por: Farina, Matteo, et al.
Publicado: (2024)

Measuring Diversity in Synthetic Datasets
por: Zhu, Yuchang, et al.
Publicado: (2025)

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

Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data
por: Yang, Shiping, et al.
Publicado: (2025)

Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
por: Zhu, Mingli, et al.
Publicado: (2024)