Pedestrian re-Identification Based on Tree Branch Network with Local and Global Learning

Abstract

Deep part-based methods in recent literature have revealed the great potential of learning local part-level representation for pedestrian image in the task of person re-identification. However, global features that capture discriminative holistic information of human body are usually ignored or not well exploited. This motivates us to investigate joint learning global and local features from pedestrian images. Specifically, in this work, we propose a novel framework termed tree branch network (TBN) for person re-identification. Given a pedestrain image, the feature maps generated by the backbone CNN, are partitioned recursively into serveral pieces, each of which is followed by a bottleneck structure that learns finer-grained features for each level in the hierarchical tree-like framework. In this way, represenations are learned in a coarseto-fine manner and finally assembled to produce more discriminative image descriptions. Experimental results demonstrate the effectiveness of the global and local feature learning method in the proposed TBN framework. We also show significant improvement in performance over state-of-the-art methods on three public benchmarks: Market-1501, CUHK-03 and DukeMTMC.

Anti‐occlusion person re‐identification via body topology information restoration and similarity evaluation

“…Existing research in this field has predominantly focused on three key aspects: learning robust representations of pedestrian images [21,22], measuring similarity between learnt features [1,[23][24][25], and re-ranking optimisation [26][27][28], all aimed at predicting whether two images correspond to the same person. Most ReID methods currently address the challenge of holistic pedestrian image matching [29][30][31][32][33]. Deng et al [34] implemented ReID in a similarity preserving generative adversarial network, which consists of Siamese network and CycleGAN, through two constraints: self-similarity of the images before and after translation, and domain dissimilarity of the translated source and a target image.…”

“…Existing research in this field has predominantly focused on three key aspects: learning robust representations of pedestrian images [21, 22], measuring similarity between learnt features [1, 23–25], and re‐ranking optimisation [26–28], all aimed at predicting whether two images correspond to the same person. Most ReID methods currently address the challenge of holistic pedestrian image matching [29–33]. Deng et al.…”

Delta tributary network—An efficient alternate approach for bottleneck layers in CNN for plant disease classification

“…Some of the other interesting bottleneck related works found in literature are [15, 16] and [17]. In [15], the authors have utilized convolution layers with bottleneck for offline hand written recognition of Chinese characters and in [16], authors have employed bottleneck layers to the feature extracted from a back bone CNN architecture for pedestrian re‐identification. Further, the authors have used the bottlenecks to learn local features within the input image.…”

Multi-Resolution Overlapping Stripes Network for Person Re-Identification

“…This technique helps our method to avoid missing features at the boundaries of the individual stripes. Lastly, inspired by the recent successful performances achieved by local and global feature fusion [5,7,8] and loss function fusion [6,8,9], various loss functions based on local and global features are employed in this work to boost the performance of the model (Section 2.2).…”

“…To address the above problems, other groups combined both global and local features. Li et al [7] fused local and global features while using mutual learning but they did not train the model with multiple loss functions. While He et al [8] used attention aware model that combines global and local features.…”