MOD-CL: Multi-label Object Detection with Constrained Loss
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909134944731136 |
|---|---|
| author | Moriyama, Sota Watanabe, Koji Inoue, Katsumi Takemura, Akihiro |
| author_facet | Moriyama, Sota Watanabe, Koji Inoue, Katsumi Takemura, Akihiro |
| contents | We introduce MOD-CL, a multi-label object detection framework that utilizes constrained loss in the training process to produce outputs that better satisfy the given requirements. In this paper, we use $\mathrm{MOD_{YOLO}}$, a multi-label object detection model built upon the state-of-the-art object detection model YOLOv8, which has been published in recent years. In Task 1, we introduce the Corrector Model and Blender Model, two new models that follow after the object detection process, aiming to generate a more constrained output. For Task 2, constrained losses have been incorporated into the $\mathrm{MOD_{YOLO}}$ architecture using Product T-Norm. The results show that these implementations are instrumental to improving the scores for both Task 1 and Task 2. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_07885 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MOD-CL: Multi-label Object Detection with Constrained Loss Moriyama, Sota Watanabe, Koji Inoue, Katsumi Takemura, Akihiro Computer Vision and Pattern Recognition Artificial Intelligence We introduce MOD-CL, a multi-label object detection framework that utilizes constrained loss in the training process to produce outputs that better satisfy the given requirements. In this paper, we use $\mathrm{MOD_{YOLO}}$, a multi-label object detection model built upon the state-of-the-art object detection model YOLOv8, which has been published in recent years. In Task 1, we introduce the Corrector Model and Blender Model, two new models that follow after the object detection process, aiming to generate a more constrained output. For Task 2, constrained losses have been incorporated into the $\mathrm{MOD_{YOLO}}$ architecture using Product T-Norm. The results show that these implementations are instrumental to improving the scores for both Task 1 and Task 2. |
| title | MOD-CL: Multi-label Object Detection with Constrained Loss |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2403.07885 |