Deep Learning for Person Re-Identification: A Survey and Outlook

  title={Deep Learning for Person Re-Identification: A Survey and Outlook},
  author={Mang Ye and Jianbing Shen and Gaojie Lin and Tao Xiang and Ling Shao and Steven C. H. Hoi},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  • Mang YeJianbing Shen S. Hoi
  • Published 13 January 2020
  • Computer Science
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
Person re-identification (Re-ID) aims at retrieving a person of interest across multiple non-overlapping cameras. With the advancement of deep neural networks and increasing demand of intelligent video surveillance, it has gained significantly increased interest in the computer vision community. By dissecting the involved components in developing a person Re-ID system, we categorize it into the closed-world and open-world settings. The widely studied closed-world setting is usually applied… 

Person Re-identification based on Robust Features in Open-world

This paper proposes a low-cost and high-efficiency method to solve shortcomings of the existing re-ID research, such as unreliable feature selection, low efficiency of feature extraction, single research variable, etc, and provides a miniature dataset which is closer to the real world and includes pedestrian changing clothes and cross-modality factor variables fusion.

An Improved Person Re-identification Method by light-weight convolutional neural network

This paper aims to improve Person Re-identification using transfer learning and application of verification loss function within the framework of Siamese network and shows that the proposed model performs better than state-of-the-art methods on the CUHK01 dataset.

Lightweight Multi-Branch Network For Person Re-Identification

A lightweight network that combines global, part-based, and channel features in a unified multi-branch architecture that builds on the resource-efficient OSNet backbone is proposed.

Second-Order Camera-Aware Color Transformation for Cross-Domain Person Re-identification

A Second-order Camera-aware Color Transformation (SCCT) that can operate on image level and align the second-order statistics of all the views of both source and target domain data with original ImageNet data statistics is proposed.

Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond

A novel generative adversarial network is proposed to address cross-resolution person re-ID, allowing query images with varying resolutions, and learns resolution-invariant image representations while being able to recover the missing details in low-resolution input images.

HAVANA: Hierarchical and Variation-Normalized Autoencoder for Person Re-identification

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.

Person Re-identification in the 3D Space

This work project 2D images to a 3D space and introduce a novel Omni-scale Graph Network (OG-Net) to learn the representation from sparse 3D points, which can learn a new type of deep re-id feature free from noisy variants, such as scale and viewpoint.

Multi-Attribute Enhancement Network for Person Search

A simple and effective model called Multi-Attribute Enhancement (MAE) which introduces attribute tags to learn local features to promote the search performance and achieves state-of-the-art among end-to-end methods.



Person Re-identification: Past, Present and Future

The history of person re-identification and its relationship with image classification and instance retrieval is introduced and two new re-ID tasks which are much closer to real-world applications are described and discussed.

Multi-scale Deep Learning Architectures for Person Re-identification

A novel multi-scale deep learning model is proposed that is able to learn deep discriminative feature representations at different scales and automatically determine the most suitable scales for matching.

Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function

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.

View Confusion Feature Learning for Person Re-Identification

  • Fangyi LiuLei Zhang
  • Computer Science
    2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
This paper proposes an end-to-end trainable framework, called View Confusion Feature Learning (VCFL), for person Re-ID across cameras, and extracts sift-guided features by using bag-of-words model to help supervise the training of deep networks and enhance the view invariance of features.

A Survey of Open-World Person Re-Identification

This survey on open-world re-ID provides a guidance for improving the usability of re-IDs technique in practical applications and summarizes the state-of-the-art methods and future directions from both narrow and generalized perspectives.

Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation

The proposed Pose Disentanglement and Adaptation Network (PDA-Net) aims at learning deep image representation with pose and domain information properly disentangled and is able to perform pose disentangling across domains without supervision in identities, and the resulting features can be applied to cross-dataset re-ID.

Person Transfer GAN to Bridge Domain Gap for Person Re-identification

A Person Transfer Generative Adversarial Network (PTGAN) is proposed to relieve the expensive costs of annotating new training samples and comprehensive experiments show that the domain gap could be substantially narrowed-down by the PTGAN.

Harmonious Attention Network for Person Re-identification

  • Wei LiXiatian ZhuS. Gong
  • Computer Science
    2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
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.

Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-free Approach

The proposed method leverages Fully Convolutional Network (FCN) to generate fix-sized spatial feature maps such that pixel-level features are consistent and can decrease the similarity of coupled images from different persons and increase that from the same person.