Push for Center Learning via Orthogonalization and Subspace Masking for Person Re-Identification

  title={Push for Center Learning via Orthogonalization and Subspace Masking for Person Re-Identification},
  author={Weinong Wang and Wenjie Pei and Qiong Cao and Shu Liu and Guangming Lu and Yu-Wing Tai},
  journal={IEEE Transactions on Image Processing},
Person re-identification aims to identify whether pairs of images belong to the same person or not. This problem is challenging due to large differences in camera views, lighting and background. One of the mainstream in learning CNN features is to design loss functions which reinforce both the class separation and intra-class compactness. In this paper, we propose a novel Orthogonal Center Learning method with Subspace Masking for person re-identification. We make the following contributions: 1… Expand
2 Citations
Learning Person Re-Identification Models From Videos With Weak Supervision
This work first cast the video person re-identification task into a multiple instance learning setting, in which person images in a video are collected into a bag, and introduces a co-person attention mechanism which mines the similarity correlations between videos with person identities in common. Expand
AAGCN: Adjacency-aware Graph Convolutional Network for person re-identification
  • Honghu Pan, Yang Bai, Zhenyu He, Chunkai Zhang
  • Computer Science
  • Knowledge-Based Systems
  • 2021


Deep person re-identification with improved embedding and efficient training
A new feature reweighting (FRW) layer is designed to explicitly emphasize the importance of each embedding dimension, thus leading to an improved embedding in a deep model for person re-identification. Expand
A Discriminatively Learned CNN Embedding for Person Reidentification
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
DeepReID: Deep Filter Pairing Neural Network for Person Re-identification
A novel filter pairing neural network (FPNN) to jointly handle misalignment, photometric and geometric transforms, occlusions and background clutter is proposed and significantly outperforms state-of-the-art methods on this dataset. 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
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
A Pose-Sensitive Embedding for Person Re-identification with Expanded Cross Neighborhood Re-ranking
This paper proposes an effective approach that incorporates both the fine and coarse pose information of the person to learn a discriminative embedding and shows that both the learned representation and the re-ranking method achieve state-of-the-art performance on a number of challenging surveillance image and video datasets. Expand
Joint Discriminative and Generative Learning for Person Re-Identification
This paper proposes a joint learning framework that couples re-id learning and data generation end-to-end and renders significant improvement over the baseline without using generated data, leading to the state-of-the-art performance on several benchmark datasets. Expand
Person Re-identification with Cascaded Pairwise Convolutions
In this paper, a novel deep architecture named BraidNet is proposed for person re-identification. BraidNet has a specially designed WConv layer, and the cascaded WConv structure learns to extract theExpand
Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification
A quadruplet deep network using a margin-based online hard negative mining is proposed based on the quadruplet loss for the person ReID, which can lead to the model output with a larger inter- class variation and a smaller intra-class variation compared to the triplet loss. Expand
Person Search via A Mask-Guided Two-Stream CNN Model
A simple yet effective re-ID method is proposed, which models foreground person and original image patches individually, and obtains enriched representations from two separate CNN streams, and achieves mAP of 83.0% on the standard person search benchmark datasets. Expand
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. Expand