Person Re-Identification With Self-Supervised Teacher for In-Box Noise
Person Re-Identification, which has been extensively researched for its wide applicability, concentrates solely on the entity of “person” within image retrieval cases. This presents a significant challenge. The person re-identification task, which follows the detector algorithm...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10908412/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850033694804279296 |
|---|---|
| author | Yonghyeok Seo Seung-Hun Kim |
| author_facet | Yonghyeok Seo Seung-Hun Kim |
| author_sort | Yonghyeok Seo |
| collection | DOAJ |
| description | Person Re-Identification, which has been extensively researched for its wide applicability, concentrates solely on the entity of “person” within image retrieval cases. This presents a significant challenge. The person re-identification task, which follows the detector algorithm step, is limited to information within the detected box. This limitation leads to what we refer to as “in-box noise,”, a type of noise that is detrimental to the predefined notion of the box-identity pair, caused by any object, other identity, or environment that obscures or interferes with the recognition of the target identity within the box. To address this in-box noise, we propose a methodology that involves training with a self-supervised teacher model. This approach exploits the relevant identity information within the box-identity pair, enabling parallel learning with the main re-identification task and interpreting the critical identity areas in the image as guided by the teacher. This methodology demonstrates impressive performance on benchmark datasets, achieving a mean average precision (mAP) of 73.4 and a rank-1 score of 88.8 on MSMT17, and an mAP of 89.7 and a rank-1 score of 95.2 on Market1501. |
| format | Article |
| id | doaj-art-aa855d362dfd45afa7847a79e35c42a9 |
| institution | DOAJ |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-aa855d362dfd45afa7847a79e35c42a92025-08-20T02:58:07ZengIEEEIEEE Access2169-35362025-01-0113398003981210.1109/ACCESS.2025.354668310908412Person Re-Identification With Self-Supervised Teacher for In-Box NoiseYonghyeok Seo0https://orcid.org/0000-0001-5629-8334Seung-Hun Kim1https://orcid.org/0000-0002-6699-2909Intelligent Robotics Research Center, Korea Electronics Technology Institute, Seongnam-si, South KoreaIntelligent Robotics Research Center, Korea Electronics Technology Institute, Seongnam-si, South KoreaPerson Re-Identification, which has been extensively researched for its wide applicability, concentrates solely on the entity of “person” within image retrieval cases. This presents a significant challenge. The person re-identification task, which follows the detector algorithm step, is limited to information within the detected box. This limitation leads to what we refer to as “in-box noise,”, a type of noise that is detrimental to the predefined notion of the box-identity pair, caused by any object, other identity, or environment that obscures or interferes with the recognition of the target identity within the box. To address this in-box noise, we propose a methodology that involves training with a self-supervised teacher model. This approach exploits the relevant identity information within the box-identity pair, enabling parallel learning with the main re-identification task and interpreting the critical identity areas in the image as guided by the teacher. This methodology demonstrates impressive performance on benchmark datasets, achieving a mean average precision (mAP) of 73.4 and a rank-1 score of 88.8 on MSMT17, and an mAP of 89.7 and a rank-1 score of 95.2 on Market1501.https://ieeexplore.ieee.org/document/10908412/Person re-identificationself-supervised learningvision-language pretrainning |
| spellingShingle | Yonghyeok Seo Seung-Hun Kim Person Re-Identification With Self-Supervised Teacher for In-Box Noise IEEE Access Person re-identification self-supervised learning vision-language pretrainning |
| title | Person Re-Identification With Self-Supervised Teacher for In-Box Noise |
| title_full | Person Re-Identification With Self-Supervised Teacher for In-Box Noise |
| title_fullStr | Person Re-Identification With Self-Supervised Teacher for In-Box Noise |
| title_full_unstemmed | Person Re-Identification With Self-Supervised Teacher for In-Box Noise |
| title_short | Person Re-Identification With Self-Supervised Teacher for In-Box Noise |
| title_sort | person re identification with self supervised teacher for in box noise |
| topic | Person re-identification self-supervised learning vision-language pretrainning |
| url | https://ieeexplore.ieee.org/document/10908412/ |
| work_keys_str_mv | AT yonghyeokseo personreidentificationwithselfsupervisedteacherforinboxnoise AT seunghunkim personreidentificationwithselfsupervisedteacherforinboxnoise |