Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-free Approach

By Lingxiao He, Jian Liang, Haiqing Li, Zhenan Sun. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018

326 citations recorded by the source corpus.

Partial person re-identification (re-id) is a challenging problem, where only several partial observations (images) of people are available for matching. However, few studies have provided flexible solutions to identifying a person in an image containing arbitrary part of the body. In this paper, we propose a fast and accurate matching method to address this problem. The proposed method leverages Fully Convolutional Network (FCN) to generate fix-sized spatial feature maps such that pixel-level features are consistent. To match a pair of person images of different sizes, a novel method called Deep Spatial feature Reconstruction (DSR) is further developed to avoid explicit alignment. Specifically, DSR exploits the reconstructing error from popular dictionary learning models to calculate the similarity between different spatial feature maps. In that way, we expect that the proposed FCN can decrease the similarity of coupled images from different persons and increase that from the same person. Experimental results on two partial person datasets demonstrate the efficiency and effectiveness of the proposed method in comparison with several state-of-the-art partial person re-id approaches. Additionally, DSR achieves competitive results on a benchmark person dataset Market1501 with 83.58% Rank-1 accuracy.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/dae580d5915cca24a321e4f8dc7209428f25720e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Yi Yang
2. Ling Shao
3. Liang Zheng
4. Luc Van Gool
5. Dacheng Tao
6. Jianbing Shen
7. Tao A. Xiang
8. Steven C. H. Hoi

Citations in the corpus

• TransReID: Transformer-based Object Re-Identification (2021, unknown): “CNN-based methods for a long time [19, 37, 36, 44, 42, 5, 12, 13, 53, 15].”
• Perceive Where to Focus: Learning Visibility-Aware Part-Level Features for Partial Person Re-Identification (2019, methodology): “When evaluating our method on these two public datasets, we train VPM on the training set of Market-1501, for fair comparison with other competitive methods, including MTRC [15], AMC+SWM [34], DSR [7], and SFR [8].”
• ABD-Net: Attentive but Diverse Person Re-Identification (2019, unknown): “03 DSR [58] (2018 CVPR) 83.”
• Pedestrian Alignment Network for Large-scale Person Re-Identification (2017, background): “[37] propose a fully convolutional network to conduct the feature reconstruction.”
• Deep Learning for Person Re-Identification: A Survey and Outlook (2020, methodology): “A fully convolutional network [224] is adopted to generate fix-sized spatial feature maps for the incomplete person images.”
• High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification (2020, methodology): “For example, DSR [8] get a 72.”
• Improving Person Re-identification by Attribute and Identity Learning (2017, unknown): “0 DSR[54] CVPR2018 Res50 82.”
• Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer (2021, methodology): “(1) The hand-crafted splitting based methods divide the image or feature map into small patches [10, 57, 12] or rigid stripes [38, 4] and then extract part features from the local patches or stripes.”