Center Prediction Loss for Re-identification

The training loss function that enforces certain training sample distribution patterns plays a critical role in building a re-identification (ReID) system. Besides the basic requirement of discrimination, i.e., the features corresponding to different identities should not be mixed, additional intraclass distribution constraints, such as features from the same identities should be close to their centers, have been adopted to construct losses. Despite the advances of various new loss functions, it is still challenging to strike the balance between the need of reducing the intra-class variation and allowing certain distribution freedom. In this paper, we propose a new loss based on center predictivity, that is, a sample must be positioned in a location of the feature space such that from it we can roughly predict the location of the center of sameclass samples. The prediction error is then regarded as a loss called Center Prediction Loss (CPL). We show that, without introducing additional hyperparameters, this new loss leads to a more flexible intra-class distribution constraint while ensuring the between-class samples are well-separated. Extensive experiments on various real-world ReID datasets show that the proposed loss can achieve superior performance and can also be complementary to existing losses.

[1]  Xiaogang Wang,et al.  DeepReID: Deep Filter Pairing Neural Network for Person Re-identification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Yu Qiao,et al.  A Discriminative Feature Learning Approach for Deep Face Recognition , 2016, ECCV.

[4]  Tiejun Huang,et al.  Deep Relative Distance Learning: Tell the Difference between Similar Vehicles , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Kihyuk Sohn,et al.  Improved Deep Metric Learning with Multi-class N-pair Loss Objective , 2016, NIPS.

[6]  Silvio Savarese,et al.  Deep Metric Learning via Lifted Structured Feature Embedding , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Yi Yang,et al.  Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in Vitro , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[8]  Liang Wang,et al.  Mask-Guided Contrastive Attention Model for Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[9]  Shaogang Gong,et al.  Harmonious Attention Network for Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[10]  Shaogang Gong,et al.  Vehicle Re-Identification in Context , 2018, GCPR.

[11]  Muhittin Gokmen,et al.  Human Semantic Parsing for Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[12]  Longhui Wei,et al.  Person Transfer GAN to Bridge Domain Gap for Person Re-identification , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[13]  Qi Tian,et al.  Beyond Part Models: Person Retrieval with Refined Part Pooling , 2017, ECCV.

[14]  Gang Wang,et al.  Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[15]  Jing Xu,et al.  Attention-Aware Compositional Network for Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[16]  Cheng Wang,et al.  Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-Identification , 2018, ECCV.

[17]  Wei Jiang,et al.  AlignedReID++: Dynamically matching local information for person re-identification , 2019, Pattern Recognit..

[18]  Yidong Li,et al.  Multi-View Learning for Vehicle Re-Identification , 2019, 2019 IEEE International Conference on Multimedia and Expo (ICME).

[19]  Wenjun Zeng,et al.  Densely Semantically Aligned Person Re-Identification , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Yang Hua,et al.  Ranked List Loss for Deep Metric Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Yunchao Wei,et al.  Horizontal Pyramid Matching for Person Re-identification , 2018, AAAI.

[22]  Ming Tang,et al.  Identity-Guided Human Semantic Parsing for Person Re-Identification , 2020, ECCV.

[23]  Rama Chellappa,et al.  The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identification , 2020, ECCV.

[24]  Yichen Wei,et al.  Circle Loss: A Unified Perspective of Pair Similarity Optimization , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Wei Jiang,et al.  A Strong Baseline and Batch Normalization Neck for Deep Person Re-Identification , 2019, IEEE Transactions on Multimedia.

[26]  Gang Yu,et al.  High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Cuiling Lan,et al.  Relation-Aware Global Attention for Person Re-Identification , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Christopher Ré,et al.  No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems , 2020, NeurIPS.

[29]  Yu-Chiang Frank Wang,et al.  Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond , 2020, ArXiv.

[30]  Farzin Aghdasi,et al.  A Strong and Efficient Baseline for Vehicle Re-Identification Using Deep Triplet Embedding , 2020, J. Artif. Intell. Soft Comput. Res..