File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICCV48922.2021.00348
- WOS: WOS:000797698903068
Supplementary
-
Citations:
- Web of Science: 0
- Appears in Collections:
Conference Paper: Preservational Learning Improves Self-supervised Medical Image Models by Reconstructing Diverse Contexts
Title | Preservational Learning Improves Self-supervised Medical Image Models by Reconstructing Diverse Contexts |
---|---|
Authors | |
Keywords | Representation learning Computer vision Protocols Codes Computational modeling |
Issue Date | 2021 |
Publisher | IEEE Computer Society. |
Citation | ICCV Workshop on Deep Multi-Task Learning in Computer Vision (Virtual), Montreal, QC, Canada, October 11-17, 2021. In Proceedings: 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW 2021), p. 3479-3489 How to Cite? |
Abstract | Preserving maximal information is one of principles of designing self-supervised learning methodologies. To reach this goal, contrastive learning adopts an implicit way which is contrasting image pairs. However, we believe it is not fully optimal to simply use the contrastive estimation for preservation. Moreover, it is necessary and complemental to introduce an explicit solution to preserve more information. From this perspective, we introduce Preservational Learning to reconstruct diverse image contexts in order to preserve more information in learned representations. Together with the contrastive loss, we present Preservational Contrastive Representation Learning (PCRL) for learning self-supervised medical representations. PCRL provides very competitive results under the pretraining-finetuning protocol, outperforming both self-supervised and supervised counterparts in 5 classification/segmentation tasks substantially. |
Persistent Identifier | http://hdl.handle.net/10722/316284 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhou, H | - |
dc.contributor.author | Lu, C | - |
dc.contributor.author | Yang, S | - |
dc.contributor.author | Han, X | - |
dc.contributor.author | Yu, Y | - |
dc.date.accessioned | 2022-09-02T06:08:46Z | - |
dc.date.available | 2022-09-02T06:08:46Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | ICCV Workshop on Deep Multi-Task Learning in Computer Vision (Virtual), Montreal, QC, Canada, October 11-17, 2021. In Proceedings: 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW 2021), p. 3479-3489 | - |
dc.identifier.uri | http://hdl.handle.net/10722/316284 | - |
dc.description.abstract | Preserving maximal information is one of principles of designing self-supervised learning methodologies. To reach this goal, contrastive learning adopts an implicit way which is contrasting image pairs. However, we believe it is not fully optimal to simply use the contrastive estimation for preservation. Moreover, it is necessary and complemental to introduce an explicit solution to preserve more information. From this perspective, we introduce Preservational Learning to reconstruct diverse image contexts in order to preserve more information in learned representations. Together with the contrastive loss, we present Preservational Contrastive Representation Learning (PCRL) for learning self-supervised medical representations. PCRL provides very competitive results under the pretraining-finetuning protocol, outperforming both self-supervised and supervised counterparts in 5 classification/segmentation tasks substantially. | - |
dc.language | eng | - |
dc.publisher | IEEE Computer Society. | - |
dc.relation.ispartof | Proceedings: 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW 2021) | - |
dc.rights | Proceedings: 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW 2021). Copyright © IEEE Computer Society. | - |
dc.subject | Representation learning | - |
dc.subject | Computer vision | - |
dc.subject | Protocols | - |
dc.subject | Codes | - |
dc.subject | Computational modeling | - |
dc.title | Preservational Learning Improves Self-supervised Medical Image Models by Reconstructing Diverse Contexts | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Yu, Y: yzyu@cs.hku.hk | - |
dc.identifier.authority | Yu, Y=rp01415 | - |
dc.identifier.doi | 10.1109/ICCV48922.2021.00348 | - |
dc.identifier.hkuros | 336345 | - |
dc.identifier.spage | 3479 | - |
dc.identifier.epage | 3489 | - |
dc.identifier.isi | WOS:000797698903068 | - |
dc.publisher.place | United States | - |