DeepMark++: Real-Time Clothing Detection at the Edge

Alexey Sidnev, Alexander Krapivin, Alexey Trushkov, Ekaterina Krasikova, Maxim Kazakov, Mikhail Viryasov; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021, pp. 2980-2988

Abstract

Clothing recognition is the most fundamental AI application challenge within the fashion domain. While existing solutions offer decent recognition accuracy, they are generally slow and require significant computational resources. In this paper we propose a single-stage approach to overcome this obstacle and deliver rapid clothing detection and keypoint estimation. Our solution is based on a multi-target network CenterNet, and we introduce several powerful post-processing techniques to enhance performance. Our most accurate model achieves results comparable to state-of-the-art solutions on the DeepFashion2 dataset, and our light and fast model runs at 17 FPS on the Huawei P40 Pro smartphone. In addition, we achieved second place in the DeepFashion2 Landmark Estimation Challenge 2020 with 0.582 mAP on the test dataset.

Related Material

[pdf]
[bibtex]
@InProceedings{Sidnev_2021_WACV, author = {Sidnev, Alexey and Krapivin, Alexander and Trushkov, Alexey and Krasikova, Ekaterina and Kazakov, Maxim and Viryasov, Mikhail}, title = {DeepMark++: Real-Time Clothing Detection at the Edge}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2021}, pages = {2980-2988} }