Deep Representation Learning With Part Loss for Person Re-Identification

@article{Yao2019DeepRL,
  title={Deep Representation Learning With Part Loss for Person Re-Identification},
  author={Hantao Yao and Shiliang Zhang and Richang Hong and Yongdong Zhang and Changsheng Xu and Qi Tian},
  journal={IEEE Transactions on Image Processing},
  year={2019},
  volume={28},
  pages={2860-2871}
}
Learning discriminative representations for unseen person images is critical for person re-identification (ReID). Most of the current approaches learn deep representations in classification tasks, which essentially minimize the empirical classification risk on the training set. As shown in our experiments, such representations easily get over-fitted on a discriminative human body part on the training set. To gain the discriminative power on unseen person images, we propose a deep representation… 
Part-based Structured Representation Learning for Person Re-identification
TLDR
A Part-based Structured Representation Learning (PSRL) for better exploiting local clues to improve the person representation and achieves competitive performance against state-of-the-art methods.
Person re-identification with fusion of hand-crafted and deep pose-based body region features
TLDR
A fusion of handcrafted features and deep feature representa- tion learned using multiple body parts to complement the global body features that achieves high performance on un- seen test images is presented.
In Defense of the Classification Loss for Person Re-Identification
TLDR
This paper proposes 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- Branches classification layers.
Deeply Associative Two-Stage Representations Learning Based on Labels Interval Extension Loss and Group Loss for Person Re-Identification
TLDR
A novel architecture named Deeply Associative Two-stage Representations Learning (DATRL) is proposed, which contains the global re-initialization stage and fully-perceptual classification stage employing two identical CNNs associatively at the same time, and shows excellent performance in improving recognition accuracy and is superior to state-of-the-art methods.
Deep Pyramidal Pooling With Attention for Person Re-Identification
TLDR
It is argued that pyramid-inspired methods capturing multi-scale information may overcome such requirements for person Re-Identification and shown that better performance than existing methods are achieved.
Person Re-Identification Based on Multi-Parts of Local Feature Network
TLDR
This paper proposes a novel, simple and efficient person re-id network called MPLFN, which combines two tasks: the classification task and the metric learning task, and achieves a better performance on three mainstream people re-identification datasets.
Person Re-Identification With Joint Verification and Identification of Identity-Attribute Labels
TLDR
A discriminative model is obtained that reaches a synergy in distinguishing different person images, as manifested with the competitive accuracy on three person ReID datasets: Market1501, DukeMTMC-reID and VIPeR.
Learning Discriminative Features with Multiple Granularities for Person Re-Identification
TLDR
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.
Aggregating Deep Pyramidal Representations for Person Re-Identification
TLDR
It is argued that a pyramid-inspired method capturing multi-scale information may overcome requirements of extensive human annotation labor or demand additional computational efforts to overcome the challenges of triplet-similarity learning.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 78 REFERENCES
Deeply-Learned Part-Aligned Representations for Person Re-identification
TLDR
This paper proposes a simple yet effective human part-aligned representation for handling the body part misalignment problem, and shows state-of-the-art results over standard datasets, Market-1501,CUHK03, CUHK01 and VIPeR.
Multi-scale Deep Learning Architectures for Person Re-identification
TLDR
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.
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.
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.
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.
Learning a Discriminative Null Space for Person Re-identification
  • Li Zhang, T. Xiang, S. Gong
  • Computer Science
    2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
TLDR
This work proposes to overcome the SSS problem in re-id distance metric learning by matching people in a discriminative null space of the training data, which has a fixed dimension, a closed-form solution and is very efficient to compute.
Scalable Person Re-identification on Supervised Smoothed Manifold
  • S. Bai, X. Bai, Q. Tian
  • Computer Science
    2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
TLDR
An unconventional manifold-preserving algorithm is proposed, which can make best use of supervision from training data, whose label information is given as pairwise constraints, scale up to large repositories with low on-line time complexity, and be plunged into most existing algorithms, serving as a generic postprocessing procedure to further boost the identification accuracies.
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.
DeepReID: Deep Filter Pairing Neural Network for Person Re-identification
TLDR
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.
Learning Mid-level Filters for Person Re-identification
TLDR
This paper proposes a novel approach of learning mid-level filters from automatically discovered patch clusters for person re-identification that is complementary to existing handcrafted low-level features, and improves the best Rank-1 matching rate on the VIPeR dataset by 14%.
...
1
2
3
4
5
...