Distilled Camera-Aware Self Training for Semi-Supervised Person Re-Identification
Person re-identification (Re-ID), which is for matching pedestrians across disjoint camera views in surveillance, has made great progress in supervised learning. However, requirement of a large number of labelled identities leads to high cost for large-scale Re-ID systems. Consequently, it is signif...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8886397/ |
| _version_ | 1818667706491076608 |
|---|---|
| author | Ancong Wu Wei-Shi Zheng Jian-Huang Lai |
| author_facet | Ancong Wu Wei-Shi Zheng Jian-Huang Lai |
| author_sort | Ancong Wu |
| collection | DOAJ |
| description | Person re-identification (Re-ID), which is for matching pedestrians across disjoint camera views in surveillance, has made great progress in supervised learning. However, requirement of a large number of labelled identities leads to high cost for large-scale Re-ID systems. Consequently, it is significant to study learning Re-ID with unlabelled data and limited labelled data, that is, semi-supervised person re-identification. When labelled data is limited, the learned model tends to overfit the data and cannot generalize well. Moreover, the scene variations between cameras lead to domain shift in the feature space, which makes mining auxiliary supervision information from unlabelled data more difficult. To address these problems, we propose a Distilled Camera-Aware Self Training framework for semi-supervised person re-identification. To alleviate the overfitting problem for learning from limited labelled data, we propose a Multi-Teacher Selective Similarity Distillation Loss to selectively aggregate the knowledge of multiple weak teacher models trained with different subsets and distill a stronger student model. Then, we exploit the unlabelled data by learning pseudo labels by clustering based on the student model for self training. To alleviate the effect of scene variations between cameras, we propose a Camera-Aware Hierarchical Clustering (CAHC) algorithm to perform intra-camera clustering and cross-camera clustering hierarchically. Experiments show that our method outperformed the state-of-the-art semi-supervised person re-identification methods. |
| first_indexed | 2024-12-17T06:24:41Z |
| format | Article |
| id | doaj.art-04762598ae724392b10fb198953dc61d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-17T06:24:41Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-04762598ae724392b10fb198953dc61d2022-12-21T22:00:19ZengIEEEIEEE Access2169-35362019-01-01715675215676310.1109/ACCESS.2019.29501228886397Distilled Camera-Aware Self Training for Semi-Supervised Person Re-IdentificationAncong Wu0https://orcid.org/0000-0002-7969-3190Wei-Shi Zheng1Jian-Huang Lai2https://orcid.org/0000-0003-3883-2024School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, ChinaSchool of Data and Computer Science, Sun Yat-sen University, Guangzhou, ChinaSchool of Data and Computer Science, Sun Yat-sen University, Guangzhou, ChinaPerson re-identification (Re-ID), which is for matching pedestrians across disjoint camera views in surveillance, has made great progress in supervised learning. However, requirement of a large number of labelled identities leads to high cost for large-scale Re-ID systems. Consequently, it is significant to study learning Re-ID with unlabelled data and limited labelled data, that is, semi-supervised person re-identification. When labelled data is limited, the learned model tends to overfit the data and cannot generalize well. Moreover, the scene variations between cameras lead to domain shift in the feature space, which makes mining auxiliary supervision information from unlabelled data more difficult. To address these problems, we propose a Distilled Camera-Aware Self Training framework for semi-supervised person re-identification. To alleviate the overfitting problem for learning from limited labelled data, we propose a Multi-Teacher Selective Similarity Distillation Loss to selectively aggregate the knowledge of multiple weak teacher models trained with different subsets and distill a stronger student model. Then, we exploit the unlabelled data by learning pseudo labels by clustering based on the student model for self training. To alleviate the effect of scene variations between cameras, we propose a Camera-Aware Hierarchical Clustering (CAHC) algorithm to perform intra-camera clustering and cross-camera clustering hierarchically. Experiments show that our method outperformed the state-of-the-art semi-supervised person re-identification methods.https://ieeexplore.ieee.org/document/8886397/Person re-identificationsemi-supervised learningknowledge distillationclustering |
| spellingShingle | Ancong Wu Wei-Shi Zheng Jian-Huang Lai Distilled Camera-Aware Self Training for Semi-Supervised Person Re-Identification IEEE Access Person re-identification semi-supervised learning knowledge distillation clustering |
| title | Distilled Camera-Aware Self Training for Semi-Supervised Person Re-Identification |
| title_full | Distilled Camera-Aware Self Training for Semi-Supervised Person Re-Identification |
| title_fullStr | Distilled Camera-Aware Self Training for Semi-Supervised Person Re-Identification |
| title_full_unstemmed | Distilled Camera-Aware Self Training for Semi-Supervised Person Re-Identification |
| title_short | Distilled Camera-Aware Self Training for Semi-Supervised Person Re-Identification |
| title_sort | distilled camera aware self training for semi supervised person re identification |
| topic | Person re-identification semi-supervised learning knowledge distillation clustering |
| url | https://ieeexplore.ieee.org/document/8886397/ |
| work_keys_str_mv | AT ancongwu distilledcameraawareselftrainingforsemisupervisedpersonreidentification AT weishizheng distilledcameraawareselftrainingforsemisupervisedpersonreidentification AT jianhuanglai distilledcameraawareselftrainingforsemisupervisedpersonreidentification |