UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Drop Loss for Person Attribute Recognition With Imbalanced Noisy-Labeled Samples

Yan, Yan; Xu, Youze; Xue, Jing-Hao; Lu, Yang; Wang, Hanzi; Zhu, Wentao; (2022) Drop Loss for Person Attribute Recognition With Imbalanced Noisy-Labeled Samples. IEEE Transactions on Cybernetics 10.1109/tcyb.2022.3173356. (In press). Green open access

[thumbnail of YanYan-YouzeXu-TCYB-2022.pdf]
Preview
Text
YanYan-YouzeXu-TCYB-2022.pdf - Accepted Version

Download (3MB) | Preview

Abstract

Person attribute recognition (PAR) aims to simultaneously predict multiple attributes of a person. Existing deep learning-based PAR methods have achieved impressive performance. Unfortunately, these methods usually ignore the fact that different attributes have an imbalance in the number of noisy-labeled samples in the PAR training datasets, thus leading to suboptimal performance. To address the above problem of imbalanced noisy-labeled samples, we propose a novel and effective loss called drop loss for PAR. In the drop loss, the attributes are treated differently in an easy-to-hard way. In particular, the noisy-labeled candidates, which are identified according to their gradient norms, are dropped with a higher drop rate for the harder attribute. Such a manner adaptively alleviates the adverse effect of imbalanced noisy-labeled samples on model learning. To illustrate the effectiveness of the proposed loss, we train a simple ResNet-50 model based on the drop loss and term it DropNet. Experimental results on two representative PAR tasks (including facial attribute recognition and pedestrian attribute recognition) demonstrate that the proposed DropNet achieves comparable or better performance in terms of both balanced accuracy and classification accuracy over several state-of-the-art PAR methods.

Type: Article
Title: Drop Loss for Person Attribute Recognition With Imbalanced Noisy-Labeled Samples
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/tcyb.2022.3173356
Publisher version: https://doi.org/10.1109/tcyb.2022.3173356
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Deep learning, gradient norm, imbalanced noisy-labeled samples, person attribute recognition (PAR)
UCL classification: UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL
URI: https://discovery.ucl.ac.uk/id/eprint/10149136
Downloads since deposit
202Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item