FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification

By Yixiao Ge, Zhuowan Li, Haiyu Zhao, Guojun Yin, Shuai Yi, Xiaogang Wang, Hongsheng Li. Neural Information Processing Systems, 2018

363 citations recorded by the source corpus.

Person re-identification (reID) is an important task that requires to retrieve a person's images from an image dataset, given one image of the person of interest. For learning robust person features, the pose variation of person images is one of the key challenges. Existing works targeting the problem either perform human alignment, or learn human-region-based representations. Extra pose information and computational cost is generally required for inference. To solve this issue, a Feature Distilling Generative Adversarial Network (FD-GAN) is proposed for learning identity-related and pose-unrelated representations. It is a novel framework based on a Siamese structure with multiple novel discriminators on human poses and identities. In addition to the discriminators, a novel same-pose loss is also integrated, which requires appearance of a same person's generated images to be similar. After learning pose-unrelated person features with pose guidance, no auxiliary pose information and additional computational cost is required during testing. Our proposed FD-GAN achieves state-of-the-art performance on three person reID datasets, which demonstrates that the effectiveness and robust feature distilling capability of the proposed FD-GAN.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/14110e0aa9b7dbe2d55414e0a79d64482c3f3908

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. Xiaogang Wang
2. Yi Yang
3. Hongsheng Li
4. Luc Van Gool
5. Wanli Ouyang
6. Dacheng Tao
7. Qi Tian
8. Ming-Hsuan Yang

Citations in the corpus

• Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification (2020, neutral): “Moreover, we almost approach fully-supervised learning performances (Sun et al., 2018; Ge et al., 2018) without any manual annotations on the target domain.”
• 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.”
• Applications of Generative Adversarial Networks (GANs): An Updated Review (2019, background): “The issue of pose variation in person images has also been addressed by Ge et al. [32].”
• 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].”
• Discriminability Distillation in Group Representation Learning (2020, background): “It is also beneficial to perform person re-identification [61,39,18,16,17,33,15] from videos.”
• 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].”
• Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID (2020, methodology): “6 Supervised learning methods on source MSMT17 Market-1501 FD-GAN [12] NeurIPS’18 77.”
• Semantics Disentangling for Text-To-Image Generation (2019, methodology): “Inspired by the advantages of Siamese structure used in different tasks [32, 33, 4, 10, 43] which can find the similarity between a pair of sequences, we treat our discriminator as an image comparator so as to preserve the semantic consistency among the generated images as long as their descriptions”
• Conditional Adversarial Generative Flow for Controllable Image Synthesis (2019, methodology): “This phenomenon results from that the underlying distribution of image conditions is difficult to measure precisely on the latent space, not to mention some multi-target 7984 978-1-7281-3293-8/19/$31.00 ©2019 IEEE DOI 10.1109/CVPR.2019.00818 tasks such as Pose-Invariant Face Recognition [6, 39] and ”
• Omni-Scale Feature Learning for Person Re-Identification (2019, neutral): “8 FDGAN [9] NeurIPS’18 ResNet 90.”
• Pose-Invariant Embedding for Deep Person Re-Identification (2017, neutral): “[32] further improve this process by designing an end-to-end network to”