Domain-Specific Block Selection and Paired-View Pseudo-Labeling for Online Test-Time Adaptation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917658993098752 |
|---|---|
| author | Yu, Yeonguk Shin, Sungho Back, Seunghyeok Ko, Minhwan Noh, Sangjun Lee, Kyoobin |
| author_facet | Yu, Yeonguk Shin, Sungho Back, Seunghyeok Ko, Minhwan Noh, Sangjun Lee, Kyoobin |
| contents | Test-time adaptation (TTA) aims to adapt a pre-trained model to a new test domain without access to source data after deployment. Existing approaches typically rely on self-training with pseudo-labels since ground-truth cannot be obtained from test data. Although the quality of pseudo labels is important for stable and accurate long-term adaptation, it has not been previously addressed. In this work, we propose DPLOT, a simple yet effective TTA framework that consists of two components: (1) domain-specific block selection and (2) pseudo-label generation using paired-view images. Specifically, we select blocks that involve domain-specific feature extraction and train these blocks by entropy minimization. After blocks are adjusted for current test domain, we generate pseudo-labels by averaging given test images and corresponding flipped counterparts. By simply using flip augmentation, we prevent a decrease in the quality of the pseudo-labels, which can be caused by the domain gap resulting from strong augmentation. Our experimental results demonstrate that DPLOT outperforms previous TTA methods in CIFAR10-C, CIFAR100-C, and ImageNet-C benchmarks, reducing error by up to 5.4%, 9.1%, and 2.9%, respectively. Also, we provide an extensive analysis to demonstrate effectiveness of our framework. Code is available at https://github.com/gist-ailab/domain-specific-block-selection-and-paired-view-pseudo-labeling-for-online-TTA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_10966 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Domain-Specific Block Selection and Paired-View Pseudo-Labeling for Online Test-Time Adaptation Yu, Yeonguk Shin, Sungho Back, Seunghyeok Ko, Minhwan Noh, Sangjun Lee, Kyoobin Computer Vision and Pattern Recognition Test-time adaptation (TTA) aims to adapt a pre-trained model to a new test domain without access to source data after deployment. Existing approaches typically rely on self-training with pseudo-labels since ground-truth cannot be obtained from test data. Although the quality of pseudo labels is important for stable and accurate long-term adaptation, it has not been previously addressed. In this work, we propose DPLOT, a simple yet effective TTA framework that consists of two components: (1) domain-specific block selection and (2) pseudo-label generation using paired-view images. Specifically, we select blocks that involve domain-specific feature extraction and train these blocks by entropy minimization. After blocks are adjusted for current test domain, we generate pseudo-labels by averaging given test images and corresponding flipped counterparts. By simply using flip augmentation, we prevent a decrease in the quality of the pseudo-labels, which can be caused by the domain gap resulting from strong augmentation. Our experimental results demonstrate that DPLOT outperforms previous TTA methods in CIFAR10-C, CIFAR100-C, and ImageNet-C benchmarks, reducing error by up to 5.4%, 9.1%, and 2.9%, respectively. Also, we provide an extensive analysis to demonstrate effectiveness of our framework. Code is available at https://github.com/gist-ailab/domain-specific-block-selection-and-paired-view-pseudo-labeling-for-online-TTA. |
| title | Domain-Specific Block Selection and Paired-View Pseudo-Labeling for Online Test-Time Adaptation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.10966 |