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

HARI MOHAN PANDEY, Yang Yang, Zichang Tan, Prayag Tiwari, Jun Wan, Zhen Lei, Guodong Guo, Stan Z. Li

Research output: Contribution to journalArticlepeer-review

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.
Original languageEnglish
Article numberVISI-D-20-00405R2
JournalInternational Journal of Computer Vision
Publication statusAccepted/In press - 5 Jun 2021

Keywords

  • Pedestrian attribute recognition
  • Attention
  • Split-and-aggregate learning
  • Feature recombination

Fingerprint

Dive into the research topics of 'Cascaded Split-and-Aggregate Learning with Feature Recombination for Pedestrian Attribute Recognition'. Together they form a unique fingerprint.

Cite this