Perceive Where to Focus: Learning Visibility-Aware Part-Level Features for Partial Person Re-Identification

By Yifan Sun, Qin Xu, Yali Li, Chi Zhang, Yikang Li, Shengjin Wang. Computer Vision and Pattern Recognition, 2019

333 citations recorded by the source corpus.

This paper considers a realistic problem in person re-identification (re-ID) task, i.e., partial re-ID. Under partial re-ID scenario, the images may contain a partial observation of a pedestrian. If we directly compare a partial pedestrian image with a holistic one, the extreme spatial misalignment significantly compromises the discriminative ability of the learned representation. We propose a Visibility-aware Part Model (VPM) for partial re-ID, which learns to perceive the visibility of regions through self-supervision. The visibility awareness allows VPM to extract region-level features and compare two images with focus on their shared regions (which are visible on both images). VPM gains two-fold benefit toward higher accuracy for partial re-ID. On the one hand, compared with learning a global feature, VPM learns region-level features and thus benefits from fine-grained information. On the other hand, with visibility awareness, VPM is capable to estimate the shared regions between two images and thus suppresses the spatial misalignment. Experimental results confirm that our method significantly improves the learned feature representation and the achieved accuracy is on par with the state of the art.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/bdcc60fbc992cf34ad714cad9a327f572c100012

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

Citations in the corpus

Cross-Modality Person Re-Identification With Shared-Specific Feature Transfer (2020, background): “Some of them treat it as a partial feature learning task and pay much attention to more powerful network structures to better discover, align, and depict the body parts [10, 38, 39, 26].”
Infrared-Visible Cross-Modal Person Re-Identification with an X Modality (2020, methodology): “It uses visible images as input, siphons off knowledge from the visible and infrared images through self-supervision (Agrawal, Carreira, and Malik 2015; Sun et al. 2019), and outputs the X images.”
Deep Learning for Person Re-Identification: A Survey and Outlook (2020, background): “Sun et al. [180] design a Visibility-aware Part Model (VPM) to extract sharable region-level features, thus suppressing the spatial misalignment in the incomplete images.”
Diverse Knowledge Distillation for End-to-End Person Search (2020, background): “In person Re-ID community, a major research line is to deal with the misalignment problem caused by occlusions, partial bodies or wrongly detected boxes (Sun et al. 2019; Guo et al. 2019; Sun et al. 2018; Zhao et al. 2020; Miao et al. 2019).”
Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer (2021, methodology): “Like some previous methods [37, 13, 5, 40], since the two partial datasets are too small, we train our model on the Market-1501 training set and use two partial datasets as test sets.”
Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification (2020, background): “Existing works have achieved human-level performance on the widely-used datasets with end-to-end deep learning [1,14,15,17,39,54], either by global [17,64] or part-level feature learning [40,39,67].”
High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification (2020, methodology): “For example, PCB [34] and FD-GAN [5] both achieve approximately 40% Rank-1 score on Occluded-Duke dataset, showing that simply using key-points information may not significantly benefit occluded ReID task.”