Gabor Convolutional Networks
- Submitting institution
-
Aberystwyth University / Prifysgol Aberystwyth
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 38986651
- Type
- D - Journal article
- DOI
-
10.1109/TIP.2018.2835143
- Title of journal
- IEEE Transactions on Image Processing
- Article number
- -
- First page
- 4357
- Volume
- 27
- Issue
- 9
- ISSN
- 1057-7149
- Open access status
- Technical exception
- Month of publication
- May
- Year of publication
- 2018
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
-
- Citation count
- 70
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- First work for incorporating Gabor filters into Deep Convolutional Neural Networks, to reinforce the robustness of learned features against image transformations. Work is accomplished by a multi-national project team, involving researchers from UK, China and USA. This study, together with the associated publicly available code (via Github) has inspired many further developments on image recognition mechanisms, e.g., Ulicny et al. 2019, TrinityCD; Kwon et al. 2019, SeoulNU; Cherukuri et al. 2020, PennsylvaniaSU; Jonnalagedda et al. 2020 UCRiverside. IEEE-TIP is the premier outlet for research in the subject area.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -