Deeply Unsupervised Patch Re-Identification for Pre-Training Object Detectors
Unsupervised pre-training aims at learning transferable features that are beneficial for downstream tasks. However, most state-of-the-art unsupervised methods concentrate on learning global representations for image-level classification tasks instead of discriminative local region representations, w...
Ausführliche Beschreibung
Bibliographische Detailangaben
Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 46(2024), 3 vom: 21. Feb., Seite 1348-1361
|
1. Verfasser: |
Ding, Jian
(VerfasserIn) |
Weitere Verfasser: |
Xie, Enze,
Xu, Hang,
Jiang, Chenhan,
Li, Zhenguo,
Luo, Ping,
Xia, Gui-Song |
Format: | Online-Aufsatz
|
Sprache: | English |
Veröffentlicht: |
2024
|
Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
Schlagworte: | Journal Article |