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 journalArticle (journal)peer-review

103 Downloads (Pure)


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
Early online date18 Jul 2021
Publication statusE-pub ahead of print - 18 Jul 2021


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


Dive into the research topics of 'Cascaded Split-and-Aggregate Learning with Feature Recombination for Pedestrian Attribute Recognition'. Together they form a unique fingerprint.
  • Skeleton based Human Activity Recognition using ConvLSTM and Guided Feature Learning

    PANDEY, HARI. MOHAN., Yadav, S. K., Tiwari, K. & Akbar, S. A., 1 Oct 2021, (E-pub ahead of print) In: Soft Computing. SOCO-D-21-00092R2.

    Research output: Contribution to journalArticle (journal)peer-review

    Open Access
    50 Citations (Scopus)
    253 Downloads (Pure)

Cite this