Cascaded Split-and-Aggregate Learning with Feature Recombination for Pedestrian Attribute Recognition

No Thumbnail Available
Journal Title
Journal ISSN
Volume Title
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
Date
2021-10
Major/Subject
Mcode
Degree programme
Language
en
Pages
13
Series
INTERNATIONAL JOURNAL OF COMPUTER VISION
Abstract
Multi-label pedestrian attribute recognition in surveillance is inherently a challenging task due to poor imaging quality, large pose variations, and so on. In this paper, we improve its performance from the following two aspects: 1) We propose a cascaded Split-and-Aggregate Learning (SAL) to capture both the individuality and commonality for all attributes, with one at feature map level and the other at the feature vector level. For the former, we split the features of each attribute by using a designed attribute-specific attention module (ASAM). For the later, the split features for each attribute are learned by using constrained losses. In both modules, the split features are aggregated by using several convolutional or fully connected layers. 2) We propose a Feature Recombination (FR) that conducts a random shuffle based on the split features over a batch of samples to synthesize more training samples, which spans the potential samples' variability. To the end, we formulate a unified framework, named CAScaded Split-and-Aggregate Learning with Feature Recombination (CAS-SAL-FR), to learn the above modules jointly and concurrently. Experiments on five popular benchmarks, including RAP, PA-100K, PETA, Market-1501 and Duke attribute datasets, show the proposed CAS-SAL-FR achieves new state-of-the-art performance.
Description
| openaire: EC/H2020/732894/EU//INTERVENE
Keywords
Other note
Citation
Yang, Y, Tan, Z, Tiwari, P, Pandey, H M, Wan, J, Lei, Z, Guo, G & Li, S Z 2021, ' Cascaded Split-and-Aggregate Learning with Feature Recombination for Pedestrian Attribute Recognition ', INTERNATIONAL JOURNAL OF COMPUTER VISION, vol. 129, no. 10, pp. 2731-2744 . https://doi.org/10.1007/s11263-021-01499-z