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

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 noisylabeled 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.

SPL-Net: Spatial-Semantic Patch Learning Network for Facial Attribute Recognition with Limited Labeled Data

“…First, the imbalanced class data distribution ) (e.g., the imbalance ratios between the minority classes and the majority classes on the Cele-bA dataset are up to 1:43) exists in facial attribute datasets. Second, many facial attributes, especially for subjective attributes, have ambiguous annotations in these datasets (Yan et al, 2022). Third, some facial attributes may not be provid- 9, where 0.2% of labeled training data on CelebA are used.…”

An Undersampling Method Approaching the Ideal Classification Boundary for Imbalance Problems

“…Kang et al [12] addressed the incorporation of a kNN filter into the undersampling method in order to exclude noise samples in the minority class. Yan et al [5] used the semantic relationship between the attributes of the problem itself to aid in the identification of noise. Indeed, kNN is a good preprocessing method for imbalance classification as long as the noise does not interfere significantly with the results.…”

“…It is well known that imbalanced problems can be solved via two methods of research: one is oversampling [5,6], whereby data sets are balanced via the random generation of samples for the minority class, and the other is undersampling, whereby data sets are balanced by performing partial sampling in the majority class and the number of samples selected is therefore reduced [7][8][9]. Although both methods have enabled significant research results to be obtained, we will focus on the undersampling method in this paper.…”