Where Are My Clothes? A Multi-Level Approach for Evaluating Deep Instance Segmentation Architectures on Fashion Images

Warren Jouanneau, Aurelie Bugeau, Marc Palyart, Nicolas Papadakis, Laurent Vezard; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, pp. 3951-3955

Abstract

In this paper we present an extensive evaluation of instance segmentation in the context of images containing clothes. We propose a multi level evaluation that completes the classical overlapping criteria given by IoU. In particular, we quantify both the contour and color content accuracy of the the predicted segmentation masks. We demonstrate that the proposed evaluation framework is relevant to obtain meaningful insights on models performance through experiments conducted on five state of the art instance segmentation methods.

Related Material

[pdf]
[bibtex]
@InProceedings{Jouanneau_2021_CVPR, author = {Jouanneau, Warren and Bugeau, Aurelie and Palyart, Marc and Papadakis, Nicolas and Vezard, Laurent}, title = {Where Are My Clothes? A Multi-Level Approach for Evaluating Deep Instance Segmentation Architectures on Fashion Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3951-3955} }