Region-Based Representations Revisited
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_ | 1866916280889507840 |
|---|---|
| author | Shlapentokh-Rothman, Michal Blume, Ansel Xiao, Yao Wu, Yuqun T V, Sethuraman Tao, Heyi Lee, Jae Yong Torres, Wilfredo Wang, Yu-Xiong Hoiem, Derek |
| author_facet | Shlapentokh-Rothman, Michal Blume, Ansel Xiao, Yao Wu, Yuqun T V, Sethuraman Tao, Heyi Lee, Jae Yong Torres, Wilfredo Wang, Yu-Xiong Hoiem, Derek |
| contents | We investigate whether region-based representations are effective for recognition. Regions were once a mainstay in recognition approaches, but pixel and patch-based features are now used almost exclusively. We show that recent class-agnostic segmenters like SAM can be effectively combined with strong unsupervised representations like DINOv2 and used for a wide variety of tasks, including semantic segmentation, object-based image retrieval, and multi-image analysis. Once the masks and features are extracted, these representations, even with linear decoders, enable competitive performance, making them well suited to applications that require custom queries. The compactness of the representation also makes it well-suited to video analysis and other problems requiring inference across many images. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_02352 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Region-Based Representations Revisited Shlapentokh-Rothman, Michal Blume, Ansel Xiao, Yao Wu, Yuqun T V, Sethuraman Tao, Heyi Lee, Jae Yong Torres, Wilfredo Wang, Yu-Xiong Hoiem, Derek Computer Vision and Pattern Recognition We investigate whether region-based representations are effective for recognition. Regions were once a mainstay in recognition approaches, but pixel and patch-based features are now used almost exclusively. We show that recent class-agnostic segmenters like SAM can be effectively combined with strong unsupervised representations like DINOv2 and used for a wide variety of tasks, including semantic segmentation, object-based image retrieval, and multi-image analysis. Once the masks and features are extracted, these representations, even with linear decoders, enable competitive performance, making them well suited to applications that require custom queries. The compactness of the representation also makes it well-suited to video analysis and other problems requiring inference across many images. |
| title | Region-Based Representations Revisited |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.02352 |