Mask-Guided Contrastive Attention Model for Person Re-identification

By Chunfeng Song, Yan Huang, Wanli Ouyang, Liang Wang. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018

617 citations recorded by the source corpus.

Person Re-identification (ReID) is an important yet challenging task in computer vision. Due to the diverse background clutters, variations on viewpoints and body poses, it is far from solved. How to extract discriminative and robust features invariant to background clutters is the core problem. In this paper, we first introduce the binary segmentation masks to construct synthetic RGB-Mask pairs as inputs, then we design a mask-guided contrastive attention model (MGCAM) to learn features separately from the body and background regions. Moreover, we propose a novel region-level triplet loss to restrain the features learnt from different regions, i.e., pulling the features from the full image and body region close, whereas pushing the features from backgrounds away. We may be the first one to successfully introduce the binary mask into person ReID task and the first one to propose region-level contrastive learning. We evaluate the proposed method on three public datasets, including MARS, Market-1501 and CUHK03. Extensive experimental results show that the proposed method is effective and achieves the state-of-the-art results. Mask and code will be released upon request.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/17092ce59ed56eb5fcbf467a889c7ec3e930f4c2

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

Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer (2021, methodology): “Existing ReID methods can be summarized to hand-crafted descriptors [47, 23], metric learning methods [56, 20, 24] and deep learning methods[38, 25, 33, 35, 45, 52, 19, 21, 34, 26, 22].”
Interaction-And-Aggregation Network for Person Re-Identification (2019, methodology): “One way is to localize body parts explicitly and combine the representations over them [59, 61, 38, 37, 20].”
Omni-Scale Feature Learning for Person Re-Identification (2019, background): “[38, 39, 26] devise attention mechanisms to focus feature learning on the foreground person regions.”
ABD-Net: Attentive but Diverse Person Re-Identification (2019, methodology): “Unless otherwise specified, we use ResNet-50 as the default backbone network due to its popularity in Re-ID [45, 46, 47, 48, 49, 11, 50, 51].”
Bilinear Attention Networks for Person Retrieval (2019, background): “Recently, several solutions have been inspired by the human visual sensing process using visual attention mechanisms [20, 43, 33, 22], to focus on the discriminative regions within a person bounding box.”
Robust Person Re-Identification by Modelling Feature Uncertainty (2019, methodology): “Deep Person ReID Models Existing deep ReID models [2, 3, 7, 10, 18, 24, 27, 30, 33, 39] typically adopt an off-the-shelf CNN architecture for deep feature learning, with recent methods mostly using ResNet [6].”
Identity-Guided Human Semantic Parsing for Person Re-Identification (2020, methodology): “Many works employ extra semantic in terms of part/pose to locate body parts [6, 27, 29, 30, 32, 34, 40, 46, 49, 56] and try to achieve the pixel-level alignment.”
Deep Learning for Person Re-Identification: A Survey and Outlook (2020, methodology): “A Mask-Guided Contrastive Attention Model (MGCAM) [84] is designed to eliminate the impact of background clutter, trained with a region-level triplet loss.”
Relation-Aware Global Attention for Person Re-Identification (2019, background): “Some works explore the external clues of human semantics (pose or mask) as attention or to use them to guide the learning of attention [39, 28, 29, 44].”
Semantics-Enhanced Adversarial Nets for Text-to-Image Synthesis (2019, background): “In other computer vision tasks, such as person search [35], person Re-identification [17, 2], object tracking [11, 45] and Image Captioning [41, 22], visual attention mechanism been studied.”
A Strong Baseline and Batch Normalization Neck for Deep Person Re-Identification (2019, background): “Mask-guided models [22]–[24] use mask as external cues to remove the background clutters in pixel level and contain body shape information.”
High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification (2020, methodology): “holistic ReID datasets Market-1501 [42] and DukeMTMCreID [28, 46], and compare with 3 vanilla ReID methods [35, 34, 24], 3 ReID methods with human-parsing information [14, 30, 27, 10] and 4 holistic ReID methods with key-points information [31, 21, 29, 26].”