In this paper, we propose an effective pipeline for clothes retrieval system which has sturdiness on large-scale real-world fashion data. Our proposed method consists of three components: detection, retrieval, and post-processing. We firstly conduct a detection task for precise retrieval on target clothes, then retrieve the corresponding items with the metric learning-based model. To improve the retrieval robustness against noise and misleading bounding boxes, we apply post-processing methods such as weighted boxes fusion and feature concatenation. With the proposed methodology, we achieved 2nd place in the DeepFashion2 Clothes Retrieval 2020 challenge.
@article{arxiv.2005.12739,
title = {An Effective Pipeline for a Real-world Clothes Retrieval System},
author = {Yang-Ho Ji and HeeJae Jun and Insik Kim and Jongtack Kim and Youngjoon Kim and Byungsoo Ko and Hyong-Keun Kook and Jingeun Lee and Sangwon Lee and Sanghyuk Park},
journal= {arXiv preprint arXiv:2005.12739},
year = {2020}
}
Comments
2nd place solution on DeepFashion2 clothes retrieval challenge in CVPR2020 workshop (CVFAD)