Relational Self-supervised Distillation with Compact Descriptors for Image Copy Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916475125628928 |
|---|---|
| author | Kim, Juntae Woo, Sungwon Nang, Jongho |
| author_facet | Kim, Juntae Woo, Sungwon Nang, Jongho |
| contents | Image copy detection is the task of detecting edited copies of any image within a reference database. While previous approaches have shown remarkable progress, the large size of their networks and descriptors remains a disadvantage, complicating their practical application. In this paper, we propose a novel method that achieves competitive performance by using a lightweight network and compact descriptors. By utilizing relational self-supervised distillation to transfer knowledge from a large network to a small network, we enable the training of lightweight networks with smaller descriptor sizes. We introduce relational self-supervised distillation for flexible representation in a smaller feature space and apply contrastive learning with a hard negative loss to prevent dimensional collapse. For the DISC2021 benchmark, ResNet-50 and EfficientNet-B0 are used as the teacher and student models, respectively, with micro average precision improving by 5.0\%/4.9\%/5.9\% for 64/128/256 descriptor sizes compared to the baseline method. The code is available at \href{https://github.com/juntae9926/RDCD}{https://github.com/juntae9926/RDCD}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_17928 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Relational Self-supervised Distillation with Compact Descriptors for Image Copy Detection Kim, Juntae Woo, Sungwon Nang, Jongho Computer Vision and Pattern Recognition Image copy detection is the task of detecting edited copies of any image within a reference database. While previous approaches have shown remarkable progress, the large size of their networks and descriptors remains a disadvantage, complicating their practical application. In this paper, we propose a novel method that achieves competitive performance by using a lightweight network and compact descriptors. By utilizing relational self-supervised distillation to transfer knowledge from a large network to a small network, we enable the training of lightweight networks with smaller descriptor sizes. We introduce relational self-supervised distillation for flexible representation in a smaller feature space and apply contrastive learning with a hard negative loss to prevent dimensional collapse. For the DISC2021 benchmark, ResNet-50 and EfficientNet-B0 are used as the teacher and student models, respectively, with micro average precision improving by 5.0\%/4.9\%/5.9\% for 64/128/256 descriptor sizes compared to the baseline method. The code is available at \href{https://github.com/juntae9926/RDCD}{https://github.com/juntae9926/RDCD}. |
| title | Relational Self-supervised Distillation with Compact Descriptors for Image Copy Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.17928 |