3A-YOLO: New Real-Time Object Detectors with Triple Discriminative Awareness and Coordinated Representations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912149998141440 |
|---|---|
| author | Wu, Xuecheng Xue, Junxiao Fu, Liangyu Nie, Jiayu Huang, Danlei Yin, Xinyi |
| author_facet | Wu, Xuecheng Xue, Junxiao Fu, Liangyu Nie, Jiayu Huang, Danlei Yin, Xinyi |
| contents | Recent research on real-time object detectors (e.g., YOLO series) has demonstrated the effectiveness of attention mechanisms for elevating model performance. Nevertheless, existing methods neglect to unifiedly deploy hierarchical attention mechanisms to construct a more discriminative YOLO head which is enriched with more useful intermediate features. To tackle this gap, this work aims to leverage multiple attention mechanisms to hierarchically enhance the triple discriminative awareness of the YOLO detection head and complementarily learn the coordinated intermediate representations, resulting in a new series detectors denoted 3A-YOLO. Specifically, we first propose a new head denoted TDA-YOLO Module, which unifiedly enhance the representations learning of scale-awareness, spatial-awareness, and task-awareness. Secondly, we steer the intermediate features to coordinately learn the inter-channel relationships and precise positional information. Finally, we perform neck network improvements followed by introducing various tricks to boost the adaptability of 3A-YOLO. Extensive experiments across COCO and VOC benchmarks indicate the effectiveness of our detectors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_07168 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | 3A-YOLO: New Real-Time Object Detectors with Triple Discriminative Awareness and Coordinated Representations Wu, Xuecheng Xue, Junxiao Fu, Liangyu Nie, Jiayu Huang, Danlei Yin, Xinyi Computer Vision and Pattern Recognition Recent research on real-time object detectors (e.g., YOLO series) has demonstrated the effectiveness of attention mechanisms for elevating model performance. Nevertheless, existing methods neglect to unifiedly deploy hierarchical attention mechanisms to construct a more discriminative YOLO head which is enriched with more useful intermediate features. To tackle this gap, this work aims to leverage multiple attention mechanisms to hierarchically enhance the triple discriminative awareness of the YOLO detection head and complementarily learn the coordinated intermediate representations, resulting in a new series detectors denoted 3A-YOLO. Specifically, we first propose a new head denoted TDA-YOLO Module, which unifiedly enhance the representations learning of scale-awareness, spatial-awareness, and task-awareness. Secondly, we steer the intermediate features to coordinately learn the inter-channel relationships and precise positional information. Finally, we perform neck network improvements followed by introducing various tricks to boost the adaptability of 3A-YOLO. Extensive experiments across COCO and VOC benchmarks indicate the effectiveness of our detectors. |
| title | 3A-YOLO: New Real-Time Object Detectors with Triple Discriminative Awareness and Coordinated Representations |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.07168 |