Domain Similarity-Perceived Label Assignment for Domain Generalized Underwater Object Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914637937639424 |
|---|---|
| author | Li, Xisheng Li, Wei Song, Pinhao Zhang, Mingjun Zhou, Jie |
| author_facet | Li, Xisheng Li, Wei Song, Pinhao Zhang, Mingjun Zhou, Jie |
| contents | The inherent characteristics and light fluctuations of water bodies give rise to the huge difference between different layers and regions in underwater environments. When the test set is collected in a different marine area from the training set, the issue of domain shift emerges, significantly compromising the model's ability to generalize. The Domain Adversarial Learning (DAL) training strategy has been previously utilized to tackle such challenges. However, DAL heavily depends on manually one-hot domain labels, which implies no difference among the samples in the same domain. Such an assumption results in the instability of DAL. This paper introduces the concept of Domain Similarity-Perceived Label Assignment (DSP). The domain label for each image is regarded as its similarity to the specified domains. Through domain-specific data augmentation techniques, we achieved state-of-the-art results on the underwater cross-domain object detection benchmark S-UODAC2020. Furthermore, we validated the effectiveness of our method in the Cityscapes dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_05401 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Domain Similarity-Perceived Label Assignment for Domain Generalized Underwater Object Detection Li, Xisheng Li, Wei Song, Pinhao Zhang, Mingjun Zhou, Jie Computer Vision and Pattern Recognition Artificial Intelligence The inherent characteristics and light fluctuations of water bodies give rise to the huge difference between different layers and regions in underwater environments. When the test set is collected in a different marine area from the training set, the issue of domain shift emerges, significantly compromising the model's ability to generalize. The Domain Adversarial Learning (DAL) training strategy has been previously utilized to tackle such challenges. However, DAL heavily depends on manually one-hot domain labels, which implies no difference among the samples in the same domain. Such an assumption results in the instability of DAL. This paper introduces the concept of Domain Similarity-Perceived Label Assignment (DSP). The domain label for each image is regarded as its similarity to the specified domains. Through domain-specific data augmentation techniques, we achieved state-of-the-art results on the underwater cross-domain object detection benchmark S-UODAC2020. Furthermore, we validated the effectiveness of our method in the Cityscapes dataset. |
| title | Domain Similarity-Perceived Label Assignment for Domain Generalized Underwater Object Detection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2401.05401 |