Coreset Selection for Object Detection
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_ | 1866913314634727424 |
|---|---|
| author | Lee, Hojun Kim, Suyoung Lee, Junhoo Yoo, Jaeyoung Kwak, Nojun |
| author_facet | Lee, Hojun Kim, Suyoung Lee, Junhoo Yoo, Jaeyoung Kwak, Nojun |
| contents | Coreset selection is a method for selecting a small, representative subset of an entire dataset. It has been primarily researched in image classification, assuming there is only one object per image. However, coreset selection for object detection is more challenging as an image can contain multiple objects. As a result, much research has yet to be done on this topic. Therefore, we introduce a new approach, Coreset Selection for Object Detection (CSOD). CSOD generates imagewise and classwise representative feature vectors for multiple objects of the same class within each image. Subsequently, we adopt submodular optimization for considering both representativeness and diversity and utilize the representative vectors in the submodular optimization process to select a subset. When we evaluated CSOD on the Pascal VOC dataset, CSOD outperformed random selection by +6.4%p in AP$_{50}$ when selecting 200 images. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_09161 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Coreset Selection for Object Detection Lee, Hojun Kim, Suyoung Lee, Junhoo Yoo, Jaeyoung Kwak, Nojun Computer Vision and Pattern Recognition Machine Learning Coreset selection is a method for selecting a small, representative subset of an entire dataset. It has been primarily researched in image classification, assuming there is only one object per image. However, coreset selection for object detection is more challenging as an image can contain multiple objects. As a result, much research has yet to be done on this topic. Therefore, we introduce a new approach, Coreset Selection for Object Detection (CSOD). CSOD generates imagewise and classwise representative feature vectors for multiple objects of the same class within each image. Subsequently, we adopt submodular optimization for considering both representativeness and diversity and utilize the representative vectors in the submodular optimization process to select a subset. When we evaluated CSOD on the Pascal VOC dataset, CSOD outperformed random selection by +6.4%p in AP$_{50}$ when selecting 200 images. |
| title | Coreset Selection for Object Detection |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2404.09161 |