Symmetric Multi-Similarity Loss for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2024
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914837958754304 |
|---|---|
| author | Wang, Xiaoqi Wang, Yi Chau, Lap-Pui |
| author_facet | Wang, Xiaoqi Wang, Yi Chau, Lap-Pui |
| contents | In this report, we present our champion solution for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge in CVPR 2024. Essentially, this challenge differs from traditional visual-text retrieval tasks by providing a correlation matrix that acts as a set of soft labels for video-text clip combinations. However, existing loss functions have not fully exploited this information. Motivated by this, we propose a novel loss function, Symmetric Multi-Similarity Loss, which offers a more precise learning objective. Together with tricks and ensemble learning, the model achieves 63.76% average mAP and 74.25% average nDCG on the public leaderboard, demonstrating the effectiveness of our approach. Our code will be released at: https://github.com/xqwang14/SMS-Loss/tree/main |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_12256 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Symmetric Multi-Similarity Loss for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2024 Wang, Xiaoqi Wang, Yi Chau, Lap-Pui Computer Vision and Pattern Recognition In this report, we present our champion solution for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge in CVPR 2024. Essentially, this challenge differs from traditional visual-text retrieval tasks by providing a correlation matrix that acts as a set of soft labels for video-text clip combinations. However, existing loss functions have not fully exploited this information. Motivated by this, we propose a novel loss function, Symmetric Multi-Similarity Loss, which offers a more precise learning objective. Together with tricks and ensemble learning, the model achieves 63.76% average mAP and 74.25% average nDCG on the public leaderboard, demonstrating the effectiveness of our approach. Our code will be released at: https://github.com/xqwang14/SMS-Loss/tree/main |
| title | Symmetric Multi-Similarity Loss for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2024 |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.12256 |