A Unified Visual Information Preservation Framework for Self-supervised Pre-Training in Medical Image Analysis
Recent advances in self-supervised learning (SSL) in computer vision are primarily comparative, whose goal is to preserve invariant and discriminative semantics in latent representations by comparing siamese image views. However, the preserved high-level semantics do not contain enough local informa...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 7 vom: 03. Juli, Seite 8020-8035
|
|---|
| 1. Verfasser: |
Zhou, Hong-Yu
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Lu, Chixiang,
Chen, Chaoqi,
Yang, Sibei,
Yu, Yizhou |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2023
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|