An Effective Pipeline for a Real-world Clothes Retrieval System
This work addresses clothes retrieval for fashion applications, but it is incremental as it builds on existing methods like detection and metric learning.
The authors tackled the problem of clothes retrieval on large-scale real-world fashion data by proposing a pipeline with detection, retrieval, and post-processing components, achieving 2nd place in the DeepFashion2 Clothes Retrieval 2020 challenge.
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.