Receptive Multi-Granularity Representation for Person Re-Identification

• Published in: IEEE transactions on image processing Vol. 29; pp. 6096 - 6109
• Main Authors: Wang, Guanshuo, Yuan, Yufeng, Li, Jiwei, Ge, Shiming, Zhou, Xi
• Format: Journal Article
• Language: English
• Published: United States IEEE 01-01-2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation models; Computer architecture; convolutional neural networks; Datasets; Feature extraction; Image enhancement; Learning; local feature learning; Machine learning; Misalignment; multiple granularity learning; Neurons; Partitions; Person re-identification; Representations; Robustness; Semantics; Task analysis
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2020.2986878

A key for person re-identification is achieving consistent local details for discriminative representation across variable environments. Current stripe-based feature learning approaches have delivered impressive accuracy, but do not make a proper trade-off between diversity, locality, and robustness, which easily suffers from part semantic inconsistency for the conflict between rigid partition and misalignment. This paper proposes a receptive multi-granularity learning approach to facilitate stripe-based feature learning. This approach performs local partition on the intermediate representations to operate receptive region ranges, rather than current approaches on input images or output features, thus can enhance the representation of locality while remaining proper local association. Toward this end, the local partitions are adaptively pooled by using significance-balanced activations for uniform stripes. Random shifting augmentation is further introduced for a higher variance of person appearing regions within bounding boxes to ease misalignment. By two-branch network architecture, different scales of discriminative identity representation can be learned. In this way, our model can provide a more comprehensive and efficient feature representation without larger model storage costs. Extensive experiments on intra-dataset and cross-dataset evaluations demonstrate the effectiveness of the proposed approach. Especially, our approach achieves a state-of-the-art accuracy of 96.2%@Rank-1 or 90.0%@mAP on the challenging Market-1501 benchmark.