Guardado en:
Detalles Bibliográficos
Autores principales: Yin, Wenting, Sun, Han, Meng, Xinru, Liu, Ningzhong, Zhou, Huiyu
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2508.20516
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911127547412480
author Yin, Wenting
Sun, Han
Meng, Xinru
Liu, Ningzhong
Zhou, Huiyu
author_facet Yin, Wenting
Sun, Han
Meng, Xinru
Liu, Ningzhong
Zhou, Huiyu
contents Continual test-time adaptation aims to continuously adapt a pre-trained model to a stream of target domain data without accessing source data. Without access to source domain data, the model focuses solely on the feature characteristics of the target data. Relying exclusively on these features can lead to confusion and introduce learning biases. Currently, many existing methods generate pseudo-labels via model predictions. However, the quality of pseudo-labels cannot be guaranteed and the problem of error accumulation must be solved. To address these challenges, we propose DCFS, a novel CTTA framework that introduces dual-path feature consistency and confidence-aware sample learning. This framework disentangles the whole feature representation of the target data into semantic-related feature and domain-related feature using dual classifiers to learn distinct feature representations. By maintaining consistency between the sub-features and the whole feature, the model can comprehensively capture data features from multiple perspectives. Additionally, to ensure that the whole feature information of the target domain samples is not overlooked, we set a adaptive threshold and calculate a confidence score for each sample to carry out loss weighted self-supervised learning, effectively reducing the noise of pseudo-labels and alleviating the problem of error accumulation. The efficacy of our proposed method is validated through extensive experimentation across various datasets, including CIFAR10-C, CIFAR100-C, and ImageNet-C, demonstrating consistent performance in continual test-time adaptation scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2508_20516
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DCFS: Continual Test-Time Adaptation via Dual Consistency of Feature and Sample
Yin, Wenting
Sun, Han
Meng, Xinru
Liu, Ningzhong
Zhou, Huiyu
Computer Vision and Pattern Recognition
Continual test-time adaptation aims to continuously adapt a pre-trained model to a stream of target domain data without accessing source data. Without access to source domain data, the model focuses solely on the feature characteristics of the target data. Relying exclusively on these features can lead to confusion and introduce learning biases. Currently, many existing methods generate pseudo-labels via model predictions. However, the quality of pseudo-labels cannot be guaranteed and the problem of error accumulation must be solved. To address these challenges, we propose DCFS, a novel CTTA framework that introduces dual-path feature consistency and confidence-aware sample learning. This framework disentangles the whole feature representation of the target data into semantic-related feature and domain-related feature using dual classifiers to learn distinct feature representations. By maintaining consistency between the sub-features and the whole feature, the model can comprehensively capture data features from multiple perspectives. Additionally, to ensure that the whole feature information of the target domain samples is not overlooked, we set a adaptive threshold and calculate a confidence score for each sample to carry out loss weighted self-supervised learning, effectively reducing the noise of pseudo-labels and alleviating the problem of error accumulation. The efficacy of our proposed method is validated through extensive experimentation across various datasets, including CIFAR10-C, CIFAR100-C, and ImageNet-C, demonstrating consistent performance in continual test-time adaptation scenarios.
title DCFS: Continual Test-Time Adaptation via Dual Consistency of Feature and Sample
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.20516