Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2403.05703 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911792414851072 |
|---|---|
| author | Wu, Junde Zhu, Jiayuan Xu, Min Jin, Yueming |
| author_facet | Wu, Junde Zhu, Jiayuan Xu, Min Jin, Yueming |
| contents | Some visual recognition tasks are more challenging then the general ones as they require professional categories of images. The previous efforts, like fine-grained vision classification, primarily introduced models tailored to specific tasks, like identifying bird species or car brands with limited scalability and generalizability. This paper aims to design a scalable and explainable model to solve Professional Visual Recognition tasks from a generic standpoint. We introduce a biologically-inspired structure named Pro-NeXt and reveal that Pro-NeXt exhibits substantial generalizability across diverse professional fields such as fashion, medicine, and art-areas previously considered disparate. Our basic-sized Pro-NeXt-B surpasses all preceding task-specific models across 12 distinct datasets within 5 diverse domains. Furthermore, we find its good scaling property that scaling up Pro-NeXt in depth and width with increasing GFlops can consistently enhances its accuracy. Beyond scalability and adaptability, the intermediate features of Pro-NeXt achieve reliable object detection and segmentation performance without extra training, highlighting its solid explainability. We will release the code to foster further research in this area. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_05703 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Not just Birds and Cars: Generic, Scalable and Explainable Models for Professional Visual Recognition Wu, Junde Zhu, Jiayuan Xu, Min Jin, Yueming Computer Vision and Pattern Recognition Some visual recognition tasks are more challenging then the general ones as they require professional categories of images. The previous efforts, like fine-grained vision classification, primarily introduced models tailored to specific tasks, like identifying bird species or car brands with limited scalability and generalizability. This paper aims to design a scalable and explainable model to solve Professional Visual Recognition tasks from a generic standpoint. We introduce a biologically-inspired structure named Pro-NeXt and reveal that Pro-NeXt exhibits substantial generalizability across diverse professional fields such as fashion, medicine, and art-areas previously considered disparate. Our basic-sized Pro-NeXt-B surpasses all preceding task-specific models across 12 distinct datasets within 5 diverse domains. Furthermore, we find its good scaling property that scaling up Pro-NeXt in depth and width with increasing GFlops can consistently enhances its accuracy. Beyond scalability and adaptability, the intermediate features of Pro-NeXt achieve reliable object detection and segmentation performance without extra training, highlighting its solid explainability. We will release the code to foster further research in this area. |
| title | Not just Birds and Cars: Generic, Scalable and Explainable Models for Professional Visual Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.05703 |