paper-with-me

홈 › Papers

Variational Continual Test-Time Adaptation

2024-02-13 · Fan Lyu, Kaile Du, Yuyang Li, Hanyu Zhao, Zhang Zhang, Guangcan Liu, Liang Wang

The prior drift is crucial in Continual Test-Time Adaptation (CTTA) methods that only use unlabeled test data, as it can cause significant error propagation. In this paper, we introduce VCoTTA, a variational Bayesian approach to measure uncertainties in CTTA. At the source stage, we transform a pre-trained deterministic model into a Bayesian Neural Network (BNN) via a variational warm-up strategy, injecting uncertainties into the model. During the testing time, we employ a mean-teacher update strategy using variational inference for the student model and exponential moving average for the teacher model. Our novel approach updates the student model by combining priors from both the source and teacher models. The evidence lower bound is formulated as the cross-entropy between the student and teacher models, along with the Kullback-Leibler (KL) divergence of the prior mixture. Experimental results on three datasets demonstrate the method's effectiveness in mitigating prior drift within the CTTA framework.

📄 PDF Abstract BibTeX arXiv:2402.08182

Code (0)

등록된 구현이 없습니다.

Tasks

Test-time AdaptationVariational Inference

Methods 이 논문이 사용한 방법론

Variational Inference 설명 없음

Similar Papers 제목 키워드 기반

Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentation

2023-03-18 · ICCV 2023 1 · Haozhi Cao, Yuecong Xu, Jianfei Yang, Pengyu Yin 외

Continual Test-Time Adaptation (CTTA) generalizes conventional Test-Time Adaptation (TTA) by assuming that the target domain is dynamic over time rather than stationary. In this paper, we explore Multi-Modal Continual Te…

3D Semantic SegmentationSemantic SegmentationTest-time Adaptation

Generalized Robust Test-Time Adaptation in Continuous Dynamic Scenarios

2023-10-07 · Shuang Li, Longhui Yuan, Binhui Xie, Tao Yang

Test-time adaptation (TTA) adapts the pre-trained models to test distributions during the inference phase exclusively employing unlabeled test data streams, which holds great value for the deployment of models in real-wo…

Test-time Adaptation

Evaluating Continual Test-Time Adaptation for Contextual and Semantic Domain Shifts

2022-08-18 · Tommie Kerssies, Mert Kılıçkaya, Joaquin Vanschoren

In this paper, our goal is to adapt a pre-trained convolutional neural network to domain shifts at test time. We do so continually with the incoming stream of test batches, without labels. The existing literature mostly …

Test-time Adaptation

Maintain Plasticity in Long-timescale Continual Test-time Adaptation

2024-12-28 · Yanshuo Wang, Xuesong Li, Jinguang Tong, Jie Hong 외

Continual test-time domain adaptation (CTTA) aims to adjust pre-trained source models to perform well over time across non-stationary target environments. While previous methods have made considerable efforts to optimize…

Domain AdaptationTest-time Adaptation

Continual Model Merging with Test-Time Adaptation for Whole-Slide Image Analysis

2026-07-06 · Duc-Thanh Le, Doanh C. Bui, Maï K. Nguyen, Khang Nguyen arxiv

Model merging offers a practical alternative to conventional continual learning by integrating independently fine-tuned models without retaining previous training data. Recent state-of-the-art model merging methods emplo…

Image ClassificationTest-time AdaptationContinual Learning