In Defense of the Classification Loss for Person Re-Identification

  title={In Defense of the Classification Loss for Person Re-Identification},
  author={Yao Zhai and Xun Guo and Yan Lu and Houqiang Li},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  • Y. ZhaiXun Guo Houqiang Li
  • Published 16 September 2018
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
The recent research for person re-identification has been focused on two trends. [] Key Method Based on that, we further propose a person re-id framework featured by channel grouping and multi-branch strategy, which divides global features into multiple channel groups and learns the discriminative channel group features by multi-branch classification layers. The extensive experiments show that our framework outperforms prior state-of-the-arts in terms of both accuracy and inference speed.

Figures and Tables from this paper

Self and Channel Attention Network for Person Re-Identification

A novel Self and Channel Attention Network (SCAN) to model long-range dependencies between channels and feature maps is proposed and multiple classifiers are added to learn discriminative global features by using classification loss.

Self Attention based multi branch Network for Person Re-Identification

  • A. MunirC. Micheloni
  • Computer Science
    2020 5th International Conference on Smart and Sustainable Technologies (SpliTech)
  • 2020
A novel self attention based multi branch(classifier) network to directly model long-range dependencies in the learned features and encourages the learning to be independent of the feature map locations is proposed.

Rethinking Classification Loss Designs for Person Re-identification with a Unified View

It is argued that triplet-based optimization can be viewed as a two-class subsampling classification, which performs classification over two sampled categories based on instance similarities, and a new meta prototypical N-tuple loss is proposed for more efficient multi- class subsampled classification.

Sampling Agnostic Feature Representation for Long-Term Person Re-Identification

A novel framework named sampling independent robust feature representation network (SirNet) that learns disentangled feature embedding from randomly chosen samples and can generate additional hard negatives/positives using the learned features, which results in better discriminability from other identities.

Multi-task person re-identification via attribute and part-based learning

A multi-branch network that jointly learns discriminative appearance and complementary attribute representations from both global and local features and mid-level semantic attributes with the supervision of identification loss and verification loss in a unified deep learning model is proposed.

Multi Branch Siamese Network For Person Re-Identification

A multi branch Siamese Deep Neural Network with multiple classifiers to overcome the above issues and creates a stronger descriptor with fine-grained information from global features of a person.

Prototype-Guided Saliency Feature Learning for Person Search

This work introduces a novel framework to learn the discriminative representation of person identity by utilizing prototype in OIM loss, and utilizes it as guidance to allow the attention network to consistently highlight multiple instances across different poses.

Pose-guided feature region-based fusion network for occluded person re-identification

A pose-guided feature region-based fusion network (PFRFN) is proposed, to utilize pose landmarks as guidance to guide local learning for a good property of local feature, and the representation learning risk is evaluated on each part loss separately.

SIF: Self-Inspirited Feature Learning for Person Re-Identification

This paper proposes a Self-Inspirited Feature Learning (SIF) method to enhance the performance of given ReID networks from the viewpoint of optimization, and designs a simple adversarial learning scheme to encourage a network to learn more discriminative person representation.

APNET: Attribute Parsing Network for Person Re-Identification

This work proposes Attribute Parsing Network (APNet), an architecture designed for both image and person attribute learning and retrievals that achieved state-of-the-art accuracy performance on both Market1501 and DukeMTMC-reID datasets.



Learning Discriminative Features with Multiple Granularities for Person Re-Identification

Comprehensive experiments implemented on the mainstream evaluation datasets including Market-1501, DukeMTMC-reid and CUHK03 indicate that the proposed end-to-end feature learning strategy robustly achieves state-of-the-art performances and outperforms any existing approaches by a large margin.

Person Re-Identification by Deep Joint Learning of Multi-Loss Classification

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.

Deep Representation Learning With Part Loss for Person Re-Identification

Experimental results on three person ReID datasets, i.e., Market1501, CUHK03, and VIPeR, show that the proposed deep representation learning procedure named part loss network outperforms existing deep representations.

Person Re-identification by Deep Learning Multi-scale Representations

A novel Deep Pyramid Feature Learning (DPFL) CNN architecture for multi-scale appearance feature fusion optimised simultaneously by concurrent per-scale re-id losses and interactive cross-scale consensus regularisation in a closed-loop design is formulated.

A Comprehensive Evaluation and Benchmark for Person Re-Identification: Features, Metrics, and Datasets

This work presents an extensive review and performance evaluation of single- and multi-shot re-id algorithms and incorporates the most recent advances in both feature extraction and metric learning.

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.

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.

Deep Transfer Learning for Person Re-Identification

A two-stepped fine-tuning strategy with proxy classifier learning is developed to transfer knowledge from auxiliary datasets to address the training data sparsity problem from the supervised and unsupervised settings.

End-to-End Comparative Attention Networks for Person Re-Identification

This paper proposes a new soft attention-based model, i.e., the end-to-end comparative attention network (CAN), specifically tailored for the task of person re-identification that outperforms well established baselines significantly and offers the new state-of-the-art performance.