Joint Discriminative and Generative Learning for Person Re-Identification

@article{Zheng2019JointDA,
  title={Joint Discriminative and Generative Learning for Person Re-Identification},
  author={Zhedong Zheng and Xiaodong Yang and Zhiding Yu and Liang Zheng and Yi Yang and Jan Kautz},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={2133-2142}
}
Person re-identification (re-id) remains challenging due to significant intra-class variations across different cameras. [...] Key Method Our model involves a generative module that separately encodes each person into an appearance code and a structure code, and a discriminative module that shares the appearance encoder with the generative module.Expand
HAVANA: Hierarchical and Variation-Normalized Autoencoder for Person Re-identification
TLDR
This paper proposes HAVANA, a novel extensible, lightweight HierArchical and VAriation-Normalized Autoencoder that learns features robust to intra-class variations and introduces a novel Jensen-Shannon triplet loss for contrastive distribution learning in Re-ID. Expand
Deep progressive attention for person re-identification
  • Changhao Wang, Guanwen Zhang, Wei Zhou
  • Computer Science, Engineering
  • J. Electronic Imaging
  • 2021
TLDR
The deep progressive attention (DPA) is proposed in a more natural manner for person Re-ID and progressively selects the most discriminative parts of a specific individual and formulates feature representation for comparison purpose. Expand
A GAN-Based Self-Training Framework for Unsupervised Domain Adaptive Person Re-Identification
TLDR
A generative adversarial networks (GAN)-based self-training framework with progressive augmentation (SPA) is proposed to obtain the robust features of the unlabeled data from the target domain, according to the preknowledge of the labeledData from the source domain. Expand
Cross-domain person re-identification by hybrid supervised and unsupervised learning
TLDR
A novel cross-domain Re-ID method combining supervised and unsupervised learning is proposed, which includes two models: a triple-condition generative adversarial network (TC-GAN) and a dual-task feature extraction network (DFE-Net). Expand
Unsupervised Attention Based Instance Discriminative Learning for Person Re-Identification
TLDR
This work proposes an unsupervised framework for person re-identification which is trained in an end-to-end manner without any pre-training and leverages a new attention mechanism that combines group convolutions to enhance spatial attention at multiple scales. Expand
Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification
TLDR
This paper proposes a joint learning framework that disentangles id-related/unrelated features and enforces adaptation to work on the id- related feature space exclusively, and outperforms the state-of-the-art methods by clear margins. Expand
Dual-Stream Reciprocal Disentanglement Learning for Domain Adaption Person Re-Identification
TLDR
A novel method named Dual-stream Reciprocal Disentanglement Learning (DRDL), which is quite efficient in learning domain-invariant features and free from image generation, which removes redundant information from id-related features. Expand
Pose Variation Adaptation for Person Re- identification
TLDR
This paper introduces a pose transfer generative adversarial network with a similarity measurement module that can reduce the probability of deep learning network over-fitting and focuses on the inferior samples which are caused by pose variations to increase the number of effective hard examples for learning discriminative features and improving the generalization ability. Expand
Learning Disentangled Representation for Robust Person Re-identification
TLDR
A new generative adversarial network, dubbed identity shuffle GAN (IS-GAN), is introduced that factorizes identity-related and -unrelated features from person images using identification labels without any auxiliary information and proposes an identity shuffling technique to regularize the disentangled features. Expand
Two-stage metric learning for cross-modality person re-identification
TLDR
A two-stage metric learning (TML) method, which uses local and global metric learning successively, and a new mixed-modality triplet loss is proposed to train more valid triplet examples. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 66 REFERENCES
Pose-Normalized Image Generation for Person Re-identification
TLDR
This work proposes a novel deep person image generation model for synthesizing realistic person images conditional on the pose based on a generative adversarial network designed specifically for pose normalization in re-id, thus termed pose-normalization GAN (PN-GAN). Expand
Learning Deep Context-Aware Features over Body and Latent Parts for Person Re-identification
TLDR
A Multi-Scale Context-Aware Network (MSCAN) to learn powerful features over full body and body parts, which can well capture the local context knowledge by stacking multi-scale convolutions in each layer. Expand
A Discriminatively Learned CNN Embedding for Person Reidentification
TLDR
This article proposes a Siamese network that simultaneously computes the identification loss and verification loss and learns a discriminative embedding and a similarity measurement at the same time, thus taking full usage of the re-ID annotations. Expand
Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-identification
TLDR
This work introduces an Transferable Joint Attribute-Identity Deep Learning (TJ-AIDL) for simultaneously learning an attribute-semantic and identity-discriminative feature representation space transferrable to any new (unseen) target domain for re-id tasks without the need for collecting new labelled training data from the target domain. Expand
Harmonious Attention Network for Person Re-identification
  • Wei Li, Xiatian Zhu, S. Gong
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
TLDR
A novel Harmonious Attention CNN (HA-CNN) model is formulated for joint learning of soft pixel attention and hard regional attention along with simultaneous optimisation of feature representations, dedicated to optimise person re-id in uncontrolled (misaligned) images. Expand
Person Re-Identification by Deep Joint Learning of Multi-Loss Classification
TLDR
This work designs a novel CNN architecture for Jointly Learning Multi-Loss (JLML) of local and global discriminative feature optimisation subject concurrently to the same re-id labelled information. Expand
Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function
TLDR
A novel multi-channel parts-based convolutional neural network model under the triplet framework for person re-identification that significantly outperforms many state-of-the-art approaches, including both traditional and deep network-based ones, on the challenging i-LIDS, VIPeR, PRID2011 and CUHK01 datasets. Expand
Pose-Driven Deep Convolutional Model for Person Re-identification
TLDR
A Pose-driven Deep Convolutional (PDC) model is proposed to learn improved feature extraction and matching models from end to end and explicitly leverages the human part cues to alleviate the pose variations and learn robust feature representations from both the global image and different local parts. Expand
Deep Attributes Driven Multi-Camera Person Re-identification
TLDR
By directly using the deep attributes with simple Cosine distance, this work has obtained surprisingly good accuracy on four person ReID datasets, and shows that a simple metric learning modular further boosts the method, making it significantly outperform many recent works. Expand
FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification
TLDR
The proposedFD-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. Expand
...
1
2
3
4
5
...