Enhanced Object Detection: A Study on Vast Vocabulary Object Detection Track for V3Det Challenge 2024
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_ | 1866910496747159552 |
|---|---|
| author | Wu, Peixi Chai, Bosong Nie, Xuan Yan, Longquan Wang, Zeyu Zhou, Qifan Wang, Boning Peng, Yansong Li, Hebei |
| author_facet | Wu, Peixi Chai, Bosong Nie, Xuan Yan, Longquan Wang, Zeyu Zhou, Qifan Wang, Boning Peng, Yansong Li, Hebei |
| contents | In this technical report, we present our findings from the research conducted on the Vast Vocabulary Visual Detection (V3Det) dataset for Supervised Vast Vocabulary Visual Detection task. How to deal with complex categories and detection boxes has become a difficulty in this track. The original supervised detector is not suitable for this task. We have designed a series of improvements, including adjustments to the network structure, changes to the loss function, and design of training strategies. Our model has shown improvement over the baseline and achieved excellent rankings on the Leaderboard for both the Vast Vocabulary Object Detection (Supervised) track and the Open Vocabulary Object Detection (OVD) track of the V3Det Challenge 2024. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09201 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhanced Object Detection: A Study on Vast Vocabulary Object Detection Track for V3Det Challenge 2024 Wu, Peixi Chai, Bosong Nie, Xuan Yan, Longquan Wang, Zeyu Zhou, Qifan Wang, Boning Peng, Yansong Li, Hebei Computer Vision and Pattern Recognition In this technical report, we present our findings from the research conducted on the Vast Vocabulary Visual Detection (V3Det) dataset for Supervised Vast Vocabulary Visual Detection task. How to deal with complex categories and detection boxes has become a difficulty in this track. The original supervised detector is not suitable for this task. We have designed a series of improvements, including adjustments to the network structure, changes to the loss function, and design of training strategies. Our model has shown improvement over the baseline and achieved excellent rankings on the Leaderboard for both the Vast Vocabulary Object Detection (Supervised) track and the Open Vocabulary Object Detection (OVD) track of the V3Det Challenge 2024. |
| title | Enhanced Object Detection: A Study on Vast Vocabulary Object Detection Track for V3Det Challenge 2024 |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.09201 |