Browsing by Author "Lei, Zhen"

Now showing 1 - 2 of 2

Cascaded Split-and-Aggregate Learning with Feature Recombination for Pedestrian Attribute Recognition
(2021-10) Yang, Yang; Tan, Zichang; Tiwari, Prayag; Pandey, Hari Mohan; Wan, Jun; Lei, Zhen; Guo, Guodong; Li, Stan Z.
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
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.
Pixel and Feature Transfer Fusion for Unsupervised Cross-Dataset Person Reidentification
(2021-11-30) Yang, Yang; Wang, Guan'an; Tiwari, Prayag; Pandey, Hari Mohan; Lei, Zhen
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
Recently, unsupervised cross-dataset person reidentification (Re-ID) has attracted more and more attention, which aims to transfer knowledge of a labeled source domain to an unlabeled target domain. There are two common frameworks: one is pixel-alignment of transferring low-level knowledge, and the other is feature-alignment of transferring high-level knowledge. In this article, we propose a novel recurrent autoencoder (RAE) framework to unify these two kinds of methods and inherit their merits. Specifically, the proposed RAE includes three modules, i.e., a feature-transfer (FT) module, a pixel-transfer (PT) module, and a fusion module. The FT module utilizes an encoder to map source and target images to a shared feature space. In the space, not only features are identity-discriminative but also the gap between source and target features is reduced. The PT module takes a decoder to reconstruct original images with its features. Here, we hope that the images reconstructed from target features are in the source style. Thus, the low-level knowledge can be propagated to the target domain. After transferring both high- and low-level knowledge with the two proposed modules above, we design another bilinear pooling layer to fuse both kinds of knowledge. Extensive experiments on Market-1501, DukeMTMC-ReID, and MSMT17 datasets show that our method significantly outperforms either pixel-alignment or feature-alignment Re-ID methods and achieves new state-of-the-art results.