YotoR-You Only Transform One Representation
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_ | 1866911894057517056 |
|---|---|
| author | Villa, José Ignacio Díaz Loncomilla, Patricio Ruiz-del-Solar, Javier |
| author_facet | Villa, José Ignacio Díaz Loncomilla, Patricio Ruiz-del-Solar, Javier |
| contents | This paper introduces YotoR (You Only Transform One Representation), a novel deep learning model for object detection that combines Swin Transformers and YoloR architectures. Transformers, a revolutionary technology in natural language processing, have also significantly impacted computer vision, offering the potential to enhance accuracy and computational efficiency. YotoR combines the robust Swin Transformer backbone with the YoloR neck and head. In our experiments, YotoR models TP5 and BP4 consistently outperform YoloR P6 and Swin Transformers in various evaluations, delivering improved object detection performance and faster inference speeds than Swin Transformer models. These results highlight the potential for further model combinations and improvements in real-time object detection with Transformers. The paper concludes by emphasizing the broader implications of YotoR, including its potential to enhance transformer-based models for image-related tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_19629 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | YotoR-You Only Transform One Representation Villa, José Ignacio Díaz Loncomilla, Patricio Ruiz-del-Solar, Javier Computer Vision and Pattern Recognition I.2.10 This paper introduces YotoR (You Only Transform One Representation), a novel deep learning model for object detection that combines Swin Transformers and YoloR architectures. Transformers, a revolutionary technology in natural language processing, have also significantly impacted computer vision, offering the potential to enhance accuracy and computational efficiency. YotoR combines the robust Swin Transformer backbone with the YoloR neck and head. In our experiments, YotoR models TP5 and BP4 consistently outperform YoloR P6 and Swin Transformers in various evaluations, delivering improved object detection performance and faster inference speeds than Swin Transformer models. These results highlight the potential for further model combinations and improvements in real-time object detection with Transformers. The paper concludes by emphasizing the broader implications of YotoR, including its potential to enhance transformer-based models for image-related tasks. |
| title | YotoR-You Only Transform One Representation |
| topic | Computer Vision and Pattern Recognition I.2.10 |
| url | https://arxiv.org/abs/2405.19629 |