Other Tokens Matter: Exploring Global and Local Features of Vision Transformers for Object Re-Identification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911850524835840 |
|---|---|
| author | Wang, Yingquan Zhang, Pingping Wang, Dong Lu, Huchuan |
| author_facet | Wang, Yingquan Zhang, Pingping Wang, Dong Lu, Huchuan |
| contents | Object Re-Identification (Re-ID) aims to identify and retrieve specific objects from images captured at different places and times. Recently, object Re-ID has achieved great success with the advances of Vision Transformers (ViT). However, the effects of the global-local relation have not been fully explored in Transformers for object Re-ID. In this work, we first explore the influence of global and local features of ViT and then further propose a novel Global-Local Transformer (GLTrans) for high-performance object Re-ID. We find that the features from last few layers of ViT already have a strong representational ability, and the global and local information can mutually enhance each other. Based on this fact, we propose a Global Aggregation Encoder (GAE) to utilize the class tokens of the last few Transformer layers and learn comprehensive global features effectively. Meanwhile, we propose the Local Multi-layer Fusion (LMF) which leverages both the global cues from GAE and multi-layer patch tokens to explore the discriminative local representations. Extensive experiments demonstrate that our proposed method achieves superior performance on four object Re-ID benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_14985 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Other Tokens Matter: Exploring Global and Local Features of Vision Transformers for Object Re-Identification Wang, Yingquan Zhang, Pingping Wang, Dong Lu, Huchuan Computer Vision and Pattern Recognition Multimedia Object Re-Identification (Re-ID) aims to identify and retrieve specific objects from images captured at different places and times. Recently, object Re-ID has achieved great success with the advances of Vision Transformers (ViT). However, the effects of the global-local relation have not been fully explored in Transformers for object Re-ID. In this work, we first explore the influence of global and local features of ViT and then further propose a novel Global-Local Transformer (GLTrans) for high-performance object Re-ID. We find that the features from last few layers of ViT already have a strong representational ability, and the global and local information can mutually enhance each other. Based on this fact, we propose a Global Aggregation Encoder (GAE) to utilize the class tokens of the last few Transformer layers and learn comprehensive global features effectively. Meanwhile, we propose the Local Multi-layer Fusion (LMF) which leverages both the global cues from GAE and multi-layer patch tokens to explore the discriminative local representations. Extensive experiments demonstrate that our proposed method achieves superior performance on four object Re-ID benchmarks. |
| title | Other Tokens Matter: Exploring Global and Local Features of Vision Transformers for Object Re-Identification |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2404.14985 |