Deeply-Learned Part-Aligned Representations for Person Re-identification

By Liming Zhao, Xi Li, Yueting Zhuang, Jingdong Wang. 2017

795 citations recorded by the source corpus.

In this paper, we address the problem of person re-identification, which refers to associating the persons captured from different cameras. We propose a simple yet effective human part-aligned representation for handling the body part misalignment problem. Our approach decomposes the human body into regions (parts) which are discriminative for person matching, accordingly computes the representations over the regions, and aggregates the similarities computed between the corresponding regions of a pair of probe and gallery images as the overall matching score. Our formulation, inspired by attention models, is a deep neural network modeling the three steps together, which is learnt through minimizing the triplet loss function without requiring body part labeling information. Unlike most existing deep learning algorithms that learn a global or spatial partition-based local representation, our approach performs human body partition, and thus is more robust to pose changes and various human spatial distributions in the person bounding box. Our approach shows state-of-the-art results over standard datasets, Market-1501, CUHK03, CUHK01 and VIPeR. 1

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Biomedical Engineering

1. Yi Yang
2. Liang Zheng
3. Zhedong Zheng
4. Tao A. Xiang
5. Qi Tian
6. Wanli Ouyang
7. Liang Wang
8. G. Wang

In Computer Vision and Pattern Recognition

1. Yi Yang
2. Luc Van Gool
3. Dacheng Tao
4. Xiaogang Wang
5. Ming-Hsuan Yang
6. Tao A. Xiang
7. Ling Shao
8. Bernt Schiele

Citations in the corpus

• DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks (2020, methodology): “While sophisticated learning based partitioning methods have been explored [36, 37, 38, 39], methods such as [40] have achieved outstanding performance with trivial deterministic splitting.”
• Omni-Scale Feature Learning for Person Re-Identification (2019, background): “Such a fine-tuning strategy has been commonly adopted by other deep learning approaches [31, 60, 74, 26, 75].”
• Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training (2018, methodology): “…GLAD* [27] 73.9 89.9 - - MultiScale [4] 73.1 88.9 - - PartLoss [29] 69.3 88.2 - - PDC* [22] 63.4 84.4 92.7 94.9 MultiLoss [13] 64.4 83.9 - - PAR [31] 63.4 81.0 92.0 94.7 HydraPlus [16] - 76.9 91.3 94.5 MultiRegion [25] 41.2 66.4 85.0 90.2 DML [30] 68.8 87.7 - - Triplet Loss [7] 69.1 84.9 94.2 -…”
• Cross Attention Network for Few-shot Classification (2019, background): “It has achieved great success in computer vision applications, such as image classification [12, 41, 27], person re-identification [10, 47, 11], image caption [29, 44, 4] and visual question answering [43, 45, 46, 30].”
• Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer (2021, methodology): “Four kinds of methods are compared, which are hand-crafted splitting based Re-ID methods [51, 38], holistic Re-ID methds with key-point information [36, 6], partial ReID methods [57, 10, 12] and occluded ReID methods [13, 5, 30, 11, 40, 60].”
• Pose-Normalized Image Generation for Person Re-identification (2017, methodology): “A number of models [39, 62, 58, 57, 23, 50, 45] are proposed to address this problem.”
• High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification (2020, methodology): “Four kinds of methods are compared, they are vanilla holistic ReID methods [41, 35], holistic ReID methods with key-points information [32, 5], partial ReID methods [45, 8, 9] and occluded ReID methods [12, 49, 10, 26].”
• Interaction-And-Aggregation Network for Person Re-Identification (2019, methodology): “Besides, human parsing method [20, 37] and body part specific attention modeling [60] had also been adopted to explicitly alleviate the pose variations problem.”
• Perceive Where to Focus: Learning Visibility-Aware Part-Level Features for Partial Person Re-Identification (2019, background): “Employing VPM adds very light computational cost, compared with popular part-based deep learning methods [23, 29, 12].”
• Deep learning in video multi-object tracking: A survey (2019, neutral): “The overall algorithm worked as follows: for every tracked target in the past frame, two score maps were computed in the current one, using PafNet and PartNet.”
• Batch Coherence-Driven Network for Part-Aware Person Re-Identification (2020, methodology): “The second strategy adopts an attention mechanism to infer the location of body parts according to the feature maps of ReID models [17], [26], [41], [42].”
• Human Semantic Parsing for Person Re-identification (2018, neutral): “2 DPAR [46] 63.”
• Occlusion Aware Facial Expression Recognition Using CNN With Attention Mechanism (2019, methodology): “re-identification [28], visual question answering [29].”
• Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification (2020, methodology): “In addition, part-based feature-learning methods [40,45,66,67] for single-modality Re-ID are typically incapable of capturing reliable part features under a large cross-domain gap [50].”
• Attention-Aware Compositional Network for Person Re-identification (2018, methodology): “One set is poseirrelevant, which includes the null space semi-supervised learning method (NFST) [49], the domain guided dropout method (JSTL) [44], the deep transfer learning method (Transfer) [16], the Singular Vector Decomposition method (SVDNet) [39], the Online Instance Matching (OIM) method [45”
• AANet: Attribute Attention Network for Person Re-Identifications (2019, methodology): “[25] follows the concept of attention model and uses a part map detector to extract multiple body regions in order to compute their corresponding representations.”