Guardado en:
| Autores principales: | , , , , |
|---|---|
| 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 |