English

Symmetric Multi-Similarity Loss for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2024

Computer Vision and Pattern Recognition 2024-06-19 v1

Abstract

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

Keywords

Cite

@article{arxiv.2406.12256,
  title  = {Symmetric Multi-Similarity Loss for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2024},
  author = {Xiaoqi Wang and Yi Wang and Lap-Pui Chau},
  journal= {arXiv preprint arXiv:2406.12256},
  year   = {2024}
}

Comments

The champion solution for Epic-Kitchen-100 Multi-Instance Retrieval Challenge