arXiv Computer Vision

Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions

The paper surveys Continual Test-Time Adaptation (CTTA), a framework that adapts pretrained computer‑vision models to non‑stationary target distributions without source data or labeled targets, while avoiding catastrophic forgetting and error accumulation. It formally defines the CTTA problem, categorizes existing methods into optimization‑based, parameter‑efficient, and architecture‑based families, and reviews representative techniques and benchmarks across standard evaluation settings. The survey also outlines current limitations and proposes future research directions, such as adapting foundation models and black‑box systems.

Hugging Face Trending Papers

Jul 9

Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions

Deep neural nets achieve remarkable performance when training and test data share the same distribution, but this assumption frequently breaks in real-world deployment, where data undergoes continual distributional shifts. Continual Test-Time Adaptation (CTTA) addresses this challenge by adapting pretrained models to non-stationary target distributions on-the-fly, without access to source data or labeled targets, while mitigating two critical failure modes: catastrophic forgetting of source knowledge and error accumulation from noisy pseudo-labels over extended time horizons.

llms computer-vision benchmarks

arXiv AI

Sep 23

Memory-Free Continual Learning with Null Space Adaptation for Zero-Shot Vision-Language Models

arXiv:2510.21175v2 Announce Type: replace Abstract: Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated remarkable zero-shot generalization, enabling deployment in a wide range...

By Yujin Jo, Taesup Kim

llms efficiency multimodal benchmarks

arXiv AI

Jul 14

Lifelong Representations: A Survey on Continual Self-Supervised Learning for Vision Models

arXiv:2607. 09785v1 Announce Type: cross Abstract: Traditionally, continual learning has assumed access to labeled data, yet many real-world applications -- such as lifelong robotics -- require models to adapt continuously from unlabeled streams.

By Sergi Masip, Alicja Dobrzeniecka, Jonathan Swinnen, Joachim Collin, Bart{\l}omiej Twardowski, Szymon {\L}ukasik, Tinne Tuytelaars

robotics efficiency multimodal benchmarks

arXiv AI

Jun 9

LargeMonitor: Monitoring Online Task-Free Continual Learning via Large Pretrained Models

arXiv:2606. 09430v1 Announce Type: cross Abstract: Online task-free continual learning (TFCL) requires intelligent agents to sequentially accumulate knowledge from an unbounded, non-stationary data stream under strict single-pass constraints and without any explicit task identifiers.

By Mingqi Yuan, Xiaoquan Sun, Shihao Luo, Jiayu Chen

agents multimodal benchmarks

arXiv Computer Vision

Sep 30

Not Every Correction Helps: Gain-Guided Continual Test-Time Adaptation

arXiv:2609.36655v1 Announce Type: new Abstract: Continual test-time adaptation (CTTA) adapts a source model to an unlabeled test stream whose distribution may change over time. Existing TTA methods o...

By Youjia Zhang, Huiling Liu, Soyun Choi, Jaehong Yoon, Sungeun Hong

benchmarks

arXiv Computer Vision

Sep 10

Distilling Image Prototypes for Guided Test-Time Adaptation

arXiv:2609.09737v1 Announce Type: new Abstract: Test-Time Adaptation (TTA) enhances the robustness of models against distribution shifts but faces two critical challenges: error accumulation from noi...

By Liwen Wang, Xingbo Dong, Iman Yi Liao, Deyin Liu, Massimo Tistarelli, Lin Yuanbo Wu, Zhe Jin

benchmarks

arXiv Machine Learning

Sep 22

SPeaR: Test-Time Adaptation with Steering Primitives for Realigning Representations

arXiv:2609.24111v1 Announce Type: new Abstract: Test-time adaptation (TTA) addresses distribution shift using only unlabeled test data. Existing methods typically adapt pretrained models by updating...

By Muhammad Sudipto Siam Dip, Ali Etemad

llms

arXiv Machine Learning

Jun 30

Audio-Visual Continual Test-Time Adaptation without Forgetting

arXiv:2602. 18528v2 Announce Type: replace Abstract: 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 cross-modal learning and eventually leads to poor accuracy.

By Sarthak Kumar Maharana, Akshay Mehra, Bhavya Ramakrishna, Yunhui Guo, Guan-Ming Su

multimodal benchmarks

arXiv Computer Vision

Sep 1

GATE: Reliability-Gated Gaussian Evidence Fusion for Training-Free Test-Time Adaptation of Vision-Language Models

arXiv:2608.29395v1 Announce Type: new Abstract: Vision-language models such as CLIP and SigLIP provide strong zero-shot recognition, but their predictions can degrade when deployed on target data tha...

By Pedram MohajerAnsari, Amir Salarpour, Run Wang, Mert D. Pes\'e

llms multimodal benchmarks

arXiv Computer Vision

Sep 3

Uniformity First: Uniformity-aware Test-time Adaptation of Vision-language Models against Image Corruption

The paper introduces UnInfo, a test‑time adaptation method for vision‑language models like CLIP that addresses image corruption—a realistic distribution shift caused by sensor conditions. UnInfo leverages uniformity‑aware confidence maximization, information‑aware loss balancing, and knowledge distillation from an EMA teacher to preserve embedding uniformity and improve zero‑shot classification accuracy. Experiments show that UnInfo outperforms existing TTA methods on corrupted image datasets.

By Kazuki Adachi, Shin'ya Yamaguchi, Tomoki Hamagami

llms rag fine-tuning efficiency multimodal

arXiv Computer Vision

Sep 30

When to Adapt: Multi-Signal Domain Shift Detection for Efficient Training-Free Adaptation in Open-Vocabulary Segmentation

arXiv:2609.37602v1 Announce Type: cross Abstract: Robust and reliable perception is essential for autonomous robots operating in real-world environments, particularly in long-term missions where envi...

By Michele Antonazzi, Alejandra C. Hernandez, Jos\'e Araujo, Olov Andersson, Patric Jensfelt

agents computer-vision robotics fine-tuning benchmarks

arXiv Machine Learning

Jun 5

Test-Time Training for Visual Foresight Vision-Language-Action Models

arXiv:2605. 08215v2 Announce Type: replace-cross Abstract: Visual Foresight VLA (VF-VLA) has become a prominent architectural choice in the recent VLA due to its impressive performance.

By Sangwu Park, Wonjoong Kim, Yeonjun In, Sein Kim, Hongseok Kang, Chanyoung Park

multimodal

Related stories