File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICCV.2019.00195
- Scopus: eid_2-s2.0-85081921597
- WOS: WOS:000531438101098
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Switchable whitening for deep representation learning
Title | Switchable whitening for deep representation learning |
---|---|
Authors | |
Issue Date | 2019 |
Publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000149 |
Citation | Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea, 27 October - 2 November 2019, p. 1863-1871 How to Cite? |
Abstract | Normalization methods are essential components in convolutional neural networks (CNNs). They either standardize or whiten data using statistics estimated in predefined sets of pixels. Unlike existing works that design normalization techniques for specific tasks, we propose Switchable Whitening (SW), which provides a general form unifying different whitening methods as well as standardization methods. SW learns to switch among these operations in an end-to-end manner. It has several advantages. First, SW adaptively selects appropriate whitening or standardization statistics for different tasks (see Fig.1), making it well suited for a wide range of tasks without manual design. Second, by integrating benefits of different normalizers, SW shows consistent improvements over its counterparts in various challenging benchmarks. Third, SW serves as a useful tool for understanding the characteristics of whitening and standardization techniques. We show that SW outperforms other alternatives on image classification (CIFAR-10/100, ImageNet), semantic segmentation (ADE20K, Cityscapes), domain adaptation (GTA5, Cityscapes), and image style transfer (COCO). For example, without bells and whistles, we achieve state-of-the-art performance with 45.33% mIoU on the ADE20K dataset. |
Persistent Identifier | http://hdl.handle.net/10722/284155 |
ISSN | 2023 SCImago Journal Rankings: 12.263 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Pan, X | - |
dc.contributor.author | Zhan, X | - |
dc.contributor.author | Shi, J | - |
dc.contributor.author | Tang, X | - |
dc.contributor.author | Luo, P | - |
dc.date.accessioned | 2020-07-20T05:56:31Z | - |
dc.date.available | 2020-07-20T05:56:31Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea, 27 October - 2 November 2019, p. 1863-1871 | - |
dc.identifier.issn | 1550-5499 | - |
dc.identifier.uri | http://hdl.handle.net/10722/284155 | - |
dc.description.abstract | Normalization methods are essential components in convolutional neural networks (CNNs). They either standardize or whiten data using statistics estimated in predefined sets of pixels. Unlike existing works that design normalization techniques for specific tasks, we propose Switchable Whitening (SW), which provides a general form unifying different whitening methods as well as standardization methods. SW learns to switch among these operations in an end-to-end manner. It has several advantages. First, SW adaptively selects appropriate whitening or standardization statistics for different tasks (see Fig.1), making it well suited for a wide range of tasks without manual design. Second, by integrating benefits of different normalizers, SW shows consistent improvements over its counterparts in various challenging benchmarks. Third, SW serves as a useful tool for understanding the characteristics of whitening and standardization techniques. We show that SW outperforms other alternatives on image classification (CIFAR-10/100, ImageNet), semantic segmentation (ADE20K, Cityscapes), domain adaptation (GTA5, Cityscapes), and image style transfer (COCO). For example, without bells and whistles, we achieve state-of-the-art performance with 45.33% mIoU on the ADE20K dataset. | - |
dc.language | eng | - |
dc.publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000149 | - |
dc.relation.ispartof | IEEE International Conference on Computer Vision (ICCV) Proceedings | - |
dc.rights | IEEE International Conference on Computer Vision (ICCV) Proceedings. Copyright © Institute of Electrical and Electronics Engineers. | - |
dc.rights | ©2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | - |
dc.title | Switchable whitening for deep representation learning | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Luo, P: pluo@hku.hk | - |
dc.identifier.authority | Luo, P=rp02575 | - |
dc.identifier.doi | 10.1109/ICCV.2019.00195 | - |
dc.identifier.scopus | eid_2-s2.0-85081921597 | - |
dc.identifier.hkuros | 311014 | - |
dc.identifier.spage | 1863 | - |
dc.identifier.epage | 1871 | - |
dc.identifier.isi | WOS:000531438101098 | - |
dc.publisher.place | United States | - |
dc.identifier.issnl | 1550-5499 | - |