English
Related papers

Related papers: Subspace Alignment for Vision-Language Model Test-…

200 papers

Test-time adaptation paradigm provides flexibility towards domain shifts by performing immediate adaptation on unlabeled target data from the source model. Vision-Language Models (VLMs) leverage their generalization capabilities for diverse…

Computer Vision and Pattern Recognition · Computer Science 2025-10-20 Jisu Han , Wonjun Hwang

Recent advances in test-time adaptation (TTA) for Vision-Language Models (VLMs) have garnered increasing attention, particularly through the use of multiple augmented views of a single image to boost zero-shot generalization. Unfortunately,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-17 Zhaohong Huang , Yuxin Zhang , Jingjing Xie , Fei Chao , Rongrong Ji

Image-to-image translation has emerged as a powerful technique in medical imaging, enabling tasks such as image denoising and cross-modality conversion. However, it suffers from limitations in handling out-of-distribution samples without…

Computer Vision and Pattern Recognition · Computer Science 2025-09-17 Irene Iele , Francesco Di Feola , Valerio Guarrasi , Paolo Soda

Test-time adaptation (TTA) aims to adapt a trained classifier using online unlabeled test data only, without any information related to the training procedure. Most existing TTA methods adapt the trained classifier using the classifier's…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Minguk Jang , Sae-Young Chung , Hye Won Chung

A foundational requirement of a deployed ML model is to generalize to data drawn from a testing distribution that is different from training. A popular solution to this problem is to adapt a pre-trained model to novel domains using only…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Kowshik Thopalli , Pavan Turaga , Jayaraman J. Thiagarajan

Test-time adaptation (TTA) has increasingly been an important topic to efficiently tackle the cross-domain distribution shift at test time for medical images from different institutions. Previous TTA methods have a common limitation of…

Computer Vision and Pattern Recognition · Computer Science 2022-05-30 Hongzheng Yang , Cheng Chen , Meirui Jiang , Quande Liu , Jianfeng Cao , Pheng Ann Heng , Qi Dou

Vision Language Models (VLMs) have become essential backbones for multimodal intelligence, yet significant safety challenges limit their real-world application. While textual inputs are often effectively safeguarded, adversarial visual…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Yi Ding , Bolian Li , Ruqi Zhang

Large-scale pretrained vision-language models like CLIP have demonstrated remarkable zero-shot image classification capabilities across diverse domains. To enhance CLIP's performance while preserving the zero-shot paradigm, various…

Computer Vision and Pattern Recognition · Computer Science 2024-06-19 Xuefeng Hu , Ke Zhang , Min Sun , Albert Chen , Cheng-Hao Kuo , Ram Nevatia

The performance of deep learning models depends heavily on test samples at runtime, and shifts from the training data distribution can significantly reduce accuracy. Test-time adaptation (TTA) addresses this by adapting models during…

Machine Learning · Computer Science 2026-02-03 Michal Danilowski , Soumyajit Chatterjee , Abhirup Ghosh

Test-time adaptation (TTA) addresses distribution shifts for streaming test data in unsupervised settings. Currently, most TTA methods can only deal with minor shifts and rely heavily on heuristic and empirical studies. To advance TTA under…

Machine Learning · Computer Science 2024-04-09 Shurui Gui , Xiner Li , Shuiwang Ji

Test-time adaptation (TTA) has emerged as a viable solution to adapt pre-trained models to domain shifts using unlabeled test data. However, TTA faces challenges of adaptation failures due to its reliance on blind adaptation to unknown test…

Machine Learning · Computer Science 2024-04-03 Taeckyung Lee , Sorn Chottananurak , Taesik Gong , Sung-Ju Lee

Test-time adaptation approaches have recently emerged as a practical solution for handling domain shift without access to the source domain data. In this paper, we propose and explore a new multi-modal extension of test-time adaptation for…

Computer Vision and Pattern Recognition · Computer Science 2022-04-28 Inkyu Shin , Yi-Hsuan Tsai , Bingbing Zhuang , Samuel Schulter , Buyu Liu , Sparsh Garg , In So Kweon , Kuk-Jin Yoon

Audio-visual continual test-time adaptation involves continually adapting a source audio-visual model at test-time, to unlabeled non-stationary domains, where either or both modalities can be distributionally shifted, which hampers online…

Machine Learning · Computer Science 2026-02-24 Sarthak Kumar Maharana , Akshay Mehra , Bhavya Ramakrishna , Yunhui Guo , Guan-Ming Su

Vision-language models suffer performance degradation under domain shift, limiting real-world applicability. Existing test-time adaptation methods are computationally intensive, rely on back-propagation, and often focus on single…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Yi Zhang , Chun-Wun Cheng , Angelica I. Aviles-Rivero , Zhihai He , Liang-Jie Zhang

Adaptation of pretrained vision-language models such as CLIP to various downstream tasks have raised great interest in recent researches. Previous works have proposed a variety of test-time adaptation (TTA) methods to achieve strong…

Computer Vision and Pattern Recognition · Computer Science 2024-10-25 Taolin Zhang , Jinpeng Wang , Hang Guo , Tao Dai , Bin Chen , Shu-Tao Xia

Due to the scarcity of annotated data and the substantial computational costs of model, conventional tuning methods in medical image segmentation face critical challenges. Current approaches to adapting pretrained models, including…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Chenlin Xu , Lei Zhang , Lituan Wang , Xinyu Pu , Pengfei Ma , Guangwu Qian , Zizhou Wang , Yan Wang

Deep networks that rely on prototypes-interpretable representations that can be related to the model input-have gained significant attention for balancing high accuracy with inherent interpretability, which makes them suitable for critical…

Machine Learning · Computer Science 2026-04-20 Mohammad Mahdi Abootorabi , Parvin Mousavi , Purang Abolmaesumi , Evan Shelhamer

Vision-language models (VLMs), e.g., CLIP, have shown remarkable potential in zero-shot image classification. However, adapting these models to new domains remains challenging, especially in unsupervised settings where labeled data is…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Eman Ali , Sathira Silva , Muhammad Haris Khan

Transductive zero-shot learning with vision-language models leverages image-image similarities within the dataset to achieve better classification accuracy compared to the inductive setting. However, there is little work that explores the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-15 Oindrila Saha , Logan Lawrence , Grant Van Horn , Subhransu Maji

Conventional test-time adaptation (TTA) approaches typically adapt the model using only a small fraction of test samples, often those with low-entropy predictions, thereby failing to fully leverage the available information in the test…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Nam Nguyen Phuong , Duc Nguyen The Minh , Phi Le Nguyen , Ehsan Abbasnejad , Minh Hoai