2018/11/17 by Zuozhuo Dai, Dai, Zuozhuo, Mingqiang Chen +7 · 2 citations
Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Face recognition and analysis #Video Surveillance and Tracking Methods
paper · pdf · doi:10.48550/arxiv.1811.07130
openalex publication_date 2018/11/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Since the person re-identification task often suffers from the problem of pose changes and occlusions, some attentive local features are often suppressed when training CNNs. In this paper, we propose the Batch DropBlock (BDB) Network which is a two branch network composed of a conventional ResNet-50 as the global branch and a feature dropping branch. The global branch encodes the global salient representations. Meanwhile, the feature dropping branch consists of an attentive feature learning module called Batch DropBlock, which randomly drops the same region of all input feature maps in a batch to reinforce the attentive feature learning of local regions. The network then concatenates features from both branches and provides a more comprehensive and spatially distributed feature representation. Albeit simple, our method achieves state-of-the-art on person re-identification and it is also applicable to general metric learning tasks. For instance, we achieve 76.4% Rank-1 accuracy on the CUHK03-Detect dataset and 83.0% Recall-1 score on the Stanford Online Products dataset, outperforming the existing works by a large margin (more than 6%).