Pose Transferrable Person Re-identification

By Jinxian Liu, Bingbing Ni, Yichao Yan, Peng Zhou, Shuo Cheng, Jianguo Hu. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018

384 citations recorded by the source corpus.

Person re-identification (ReID) is an important task in the field of intelligent security. A key challenge is how to capture human pose variations, while existing benchmarks (i.e., Market1501, DukeMTMC-reID, CUHK03, etc.) do NOT provide sufficient pose coverage to train a robust ReID system. To address this issue, we propose a pose-transferrable person ReID framework which utilizes posetransferred sample augmentations (i.e., with ID supervision) to enhance ReID model training. On one hand, novel training samples with rich pose variations are generated via transferring pose instances from MARS dataset, and they are added into the target dataset to facilitate robust training. On the other hand, in addition to the conventional discriminator of GAN (i.e., to distinguish between REAL/FAKE samples), we propose a novel guider sub-network which encourages the generated sample (i.e., with novel pose) towards better satisfying the ReID loss (i.e., cross-entropy ReID loss, triplet ReID loss). In the meantime, an alternative optimization procedure is proposed to train the proposed Generator-Guider-Discriminator network. Experimental results on Market-1501, DukeMTMC-reID and CUHK03 show that our method achieves great performance improvement, and outperforms most state-of-the-art methods without elaborate designing the ReID model.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/df4ed9983f7114ca4f0ab71f1476c0bf7521e317

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. Qi Tian
5. Mang Ye
6. Tao A. Xiang
7. Yu Wu
8. Ling Shao

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Yi Yang
3. Ling Shao
4. Ming-Hsuan Yang
5. Dacheng Tao
6. Xiaogang Wang
7. Qi Tian
8. Trevor Darrell

Citations in the corpus

• Variational Convolutional Neural Network Pruning (2019, methodology): “Deep convolutional neural networks have achieved a significant success in computer vision community, such as object recognition [13, 25, 37, 44], semantic segmentation [2, 28], object detection [9, 26] and video analysis [45, 46].”
• Pose-Invariant Embedding for Deep Person Re-Identification (2017, methodology): “of various poses [31]–[33].”
• Deep Learning for Person Re-Identification: A Survey and Outlook (2020, methodology): “Pose constraints are incorporated in [114] to improve the quality of the generated person images, generating the person images with new pose variants.”
• Joint Discriminative and Generative Learning for Person Re-Identification (2019, methodology): “Similarly, pose is also used in [10,27,31] to generate images of a pedestrian in different poses to make learned features more robust to pose variances.”
• Cluster Contrast for Unsupervised Person Re-Identification (2021, positive): “In supervised person re-ID, the batch hard triplet loss has proved to be effective solutions to improve the re-ID performance [3,9,10,18,32,42,46,63,69].”
• Pose-Guided Feature Alignment for Occluded Person Re-Identification (2019, methodology): “Recently, some person re-id methods [9, 33, 29, 23, 30] employ pose information to facilitate person re-id models.”
• 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].”
• Identity-Guided Human Semantic Parsing for Person Re-Identification (2020, background): “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.”
• University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization (2020, methodology): “In light of the recent practice using synthetic training data [14, 17, 26, 38], we propose a multi-view multi-source dataset called University-1652, containing synthetic drone-view images.”
• Learning to Reduce Dual-Level Discrepancy for Infrared-Visible Person Re-Identification (2019, background): “[11] proposed a pose transferrable framework for generating samples with rich pose variations.”
• Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification (2019, background): “Most of the existing work is categorized in two ways as follows: pose transfer [18, 22, 6] and style transfer [32, 19, 5, 31].”
• 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].”