Cover Image

The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sheng, Lijun, Liang, Jian, He, Ran, Wang, Zilei, Tan, Tieniu
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Towards Compatible Fine-tuning for Vision-Language Model Updates
by: Wang, Zhengbo, et al.
Published: (2024)

R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning
by: Sheng, Lijun, et al.
Published: (2025)

A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
by: Wang, Zhengbo, et al.
Published: (2024)

Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models
by: Wang, Zhengbo, et al.
Published: (2024)

A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
by: Liang, Jian, et al.
Published: (2023)

Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization
by: Liang, Jian, et al.
Published: (2023)

STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay
by: Yu, Yongcan, et al.
Published: (2024)

Exploring Vacant Classes in Label-Skewed Federated Learning
by: Guo, Kuangpu, et al.
Published: (2024)

Cooperative Pseudo Labeling for Unsupervised Federated Classification
by: Guo, Kuangpu, et al.
Published: (2025)

Prototypical Distillation and Debiased Tuning for Black-box Unsupervised Domain Adaptation
by: Liang, Jian, et al.
Published: (2024)

Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging
by: Guo, Kuangpu, et al.
Published: (2025)

Adapting Vision-Language Models Without Labels: A Comprehensive Survey
by: Dong, Hao, et al.
Published: (2025)

Training-Free Test-Time Adaptation with Brownian Distance Covariance in Vision-Language Models
by: Zhang, Yi, et al.
Published: (2026)

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

Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common Corruptions
by: Bao, Wenxuan, et al.
Published: (2025)

AUTO: Adaptive Outlier Optimization for Test-Time OOD Detection
by: Yang, Puning, et al.
Published: (2023)

Fair Context Learning for Evidence-Balanced Test-Time Adaptation in Vision-Language Models
by: Yun, Sanggeon, et al.
Published: (2026)

Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models
by: Wu, Junfei, et al.
Published: (2024)

Qwen Look Again: Guiding Vision-Language Reasoning Models to Re-attention Visual Information
by: Chu, Xu, et al.
Published: (2025)

Bridging Modalities via Progressive Re-alignment for Multimodal Test-Time Adaptation
by: Li, Jiacheng, et al.
Published: (2025)

Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-Training
by: Zhang, Wenyu, et al.
Published: (2024)

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

On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning
by: Su, Yongyi, et al.
Published: (2024)

Learning to Generate Gradients for Test-Time Adaptation via Test-Time Training Layers
by: Deng, Qi, et al.
Published: (2024)

Efficient Test-Time Scaling for Small Vision-Language Models
by: Kaya, Mehmet Onurcan, et al.
Published: (2025)

Two Simple Principles for Diffusion-Based Test-Time Adaptation
by: Song, Kaiyu, et al.
Published: (2023)

Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models
by: Zhang, Ce, et al.
Published: (2024)

PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understanding
by: Jiang, Jincen, et al.
Published: (2024)

Mitigating the Bias in the Model for Continual Test-Time Adaptation
by: Chung, Inseop, et al.
Published: (2024)

ZOTTA: Test-Time Adaptation with Gradient-Free Zeroth-Order Optimization
by: Zhang, Ronghao, et al.
Published: (2026)

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

Protecting Model Adaptation from Trojans in the Unlabeled Data
by: Sheng, Lijun, et al.
Published: (2024)

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

TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration
by: Li, Chunxiao, et al.
Published: (2026)

When Test-Time Adaptation Meets Self-Supervised Models
by: Han, Jisu, et al.
Published: (2025)

Test-Time Adaptation for Depth Completion
by: Park, Hyoungseob, et al.
Published: (2024)

Buffer layers for Test-Time Adaptation
by: Kim, Hyeongyu, et al.
Published: (2025)

BendVLM: Test-Time Debiasing of Vision-Language Embeddings
by: Gerych, Walter, et al.
Published: (2024)

Leveraging Geometric Visual Illusions as Perceptual Inductive Biases for Vision Models
by: Yang, Haobo, et al.
Published: (2025)

Unraveling Batch Normalization for Realistic Test-Time Adaptation
by: Su, Zixian, et al.
Published: (2023)