Pedestrian Attribute Recognition as Label-balanced Multi-label Learning
This work addresses data imbalance issues in pedestrian attribute recognition, which is important for surveillance and security applications, but it is incremental as it builds on existing multi-label learning methods.
The paper tackles the problem of skewed data distribution in pedestrian attribute recognition, which leads to label and semantics imbalances, by proposing a framework that decouples label-balanced data re-sampling from attribute co-occurrence and uses Bayesian feature augmentation to diversify semantics. It achieves best accuracy on various benchmarks with minimal computational cost.
Rooting in the scarcity of most attributes, realistic pedestrian attribute datasets exhibit unduly skewed data distribution, from which two types of model failures are delivered: (1) label imbalance: model predictions lean greatly towards the side of majority labels; (2) semantics imbalance: model is easily overfitted on the under-represented attributes due to their insufficient semantic diversity. To render perfect label balancing, we propose a novel framework that successfully decouples label-balanced data re-sampling from the curse of attributes co-occurrence, i.e., we equalize the sampling prior of an attribute while not biasing that of the co-occurred others. To diversify the attributes semantics and mitigate the feature noise, we propose a Bayesian feature augmentation method to introduce true in-distribution novelty. Handling both imbalances jointly, our work achieves best accuracy on various popular benchmarks, and importantly, with minimal computational budget.