抄録
Deep metric learning has been widely used for image retrieval and verification tasks. Traditional contrastive loss and triplet loss depend highly on the selection of pair/triplet images. It makes the training process unstable and uncomplete. In this paper, we propose a novel global level loss function that considers histograms for intra distances within class and inter distances between different classes. We compared two forms of global level loss (hard selection based loss and soft selection based loss) and both achieved better result than traditional triplet loss, multi-class N pair loss and other related works. The experiment is conducted on the person re-identification dataset Market 1501 and DukeMTMC-reID.
| 元の言語 | English |
|---|---|
| ホスト出版物のタイトル | 2018 Joint 7th International Conference on Informatics, Electronics and Vision and 2nd International Conference on Imaging, Vision and Pattern Recognition, ICIEV-IVPR 2018 |
| 出版者 | Institute of Electrical and Electronics Engineers Inc. |
| ページ | 426-431 |
| ページ数 | 6 |
| ISBN（電子版） | 9781538651612 |
| DOI | |
| 出版物ステータス | Published - 2019 2 12 |
| イベント | Joint 7th International Conference on Informatics, Electronics and Vision and 2nd International Conference on Imaging, Vision and Pattern Recognition, ICIEV-IVPR 2018 - Kitakyushu, Japan 継続期間: 2018 6 25 → 2018 6 28 |
出版物シリーズ
| 名前 | 2018 Joint 7th International Conference on Informatics, Electronics and Vision and 2nd International Conference on Imaging, Vision and Pattern Recognition, ICIEV-IVPR 2018 |
|---|
Conference
| Conference | Joint 7th International Conference on Informatics, Electronics and Vision and 2nd International Conference on Imaging, Vision and Pattern Recognition, ICIEV-IVPR 2018 |
|---|---|
| 国 | Japan |
| 市 | Kitakyushu |
| 期間 | 18/6/25 → 18/6/28 |
Fingerprint
Keywords
ASJC Scopus subject areas
- Signal Processing
- Control and Optimization
- Artificial Intelligence
- Computer Vision and Pattern Recognition
- Information Systems
これを引用
Deep metric learning with online hard and soft selection for person re-identification. / Yu, Mingyang; Kamata, Seiichiro.
2018 Joint 7th International Conference on Informatics, Electronics and Vision and 2nd International Conference on Imaging, Vision and Pattern Recognition, ICIEV-IVPR 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 426-431 8641037 (2018 Joint 7th International Conference on Informatics, Electronics and Vision and 2nd International Conference on Imaging, Vision and Pattern Recognition, ICIEV-IVPR 2018).研究成果: Conference contribution
}
TY - GEN
T1 - Deep metric learning with online hard and soft selection for person re-identification
AU - Yu, Mingyang
AU - Kamata, Seiichiro
PY - 2019/2/12
Y1 - 2019/2/12
N2 - Deep metric learning has been widely used for image retrieval and verification tasks. Traditional contrastive loss and triplet loss depend highly on the selection of pair/triplet images. It makes the training process unstable and uncomplete. In this paper, we propose a novel global level loss function that considers histograms for intra distances within class and inter distances between different classes. We compared two forms of global level loss (hard selection based loss and soft selection based loss) and both achieved better result than traditional triplet loss, multi-class N pair loss and other related works. The experiment is conducted on the person re-identification dataset Market 1501 and DukeMTMC-reID.
AB - Deep metric learning has been widely used for image retrieval and verification tasks. Traditional contrastive loss and triplet loss depend highly on the selection of pair/triplet images. It makes the training process unstable and uncomplete. In this paper, we propose a novel global level loss function that considers histograms for intra distances within class and inter distances between different classes. We compared two forms of global level loss (hard selection based loss and soft selection based loss) and both achieved better result than traditional triplet loss, multi-class N pair loss and other related works. The experiment is conducted on the person re-identification dataset Market 1501 and DukeMTMC-reID.
KW - Deep metric learning
KW - Feature embedding
KW - Per-son Re-identification
UR - http://www.scopus.com/inward/record.url?scp=85063221482&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85063221482&partnerID=8YFLogxK
U2 - 10.1109/ICIEV.2018.8641037
DO - 10.1109/ICIEV.2018.8641037
M3 - Conference contribution
T3 - 2018 Joint 7th International Conference on Informatics, Electronics and Vision and 2nd International Conference on Imaging, Vision and Pattern Recognition, ICIEV-IVPR 2018
SP - 426
EP - 431
BT - 2018 Joint 7th International Conference on Informatics, Electronics and Vision and 2nd International Conference on Imaging, Vision and Pattern Recognition, ICIEV-IVPR 2018
PB - Institute of Electrical and Electronics Engineers Inc.
ER -