Enhancing Weakly-Supervised Object Detection on Static Images through (Hallucinated) Motion
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916394405199872 |
|---|---|
| author | Gungor, Cagri Kovashka, Adriana |
| author_facet | Gungor, Cagri Kovashka, Adriana |
| contents | While motion has garnered attention in various tasks, its potential as a modality for weakly-supervised object detection (WSOD) in static images remains unexplored. Our study introduces an approach to enhance WSOD methods by integrating motion information. This method involves leveraging hallucinated motion from static images to improve WSOD on image datasets, utilizing a Siamese network for enhanced representation learning with motion, addressing camera motion through motion normalization, and selectively training images based on object motion. Experimental validation on the COCO and YouTube-BB datasets demonstrates improvements over a state-of-the-art method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_09616 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Weakly-Supervised Object Detection on Static Images through (Hallucinated) Motion Gungor, Cagri Kovashka, Adriana Computer Vision and Pattern Recognition While motion has garnered attention in various tasks, its potential as a modality for weakly-supervised object detection (WSOD) in static images remains unexplored. Our study introduces an approach to enhance WSOD methods by integrating motion information. This method involves leveraging hallucinated motion from static images to improve WSOD on image datasets, utilizing a Siamese network for enhanced representation learning with motion, addressing camera motion through motion normalization, and selectively training images based on object motion. Experimental validation on the COCO and YouTube-BB datasets demonstrates improvements over a state-of-the-art method. |
| title | Enhancing Weakly-Supervised Object Detection on Static Images through (Hallucinated) Motion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.09616 |