A Simple Stochastic Regularization Technique for Avoiding Overfitting in Low Resource Image Classification

Simple item page
dc.contributor.authorJi, Ya Tuen_US
dc.contributor.authorWang, Bai Lunen_US
dc.contributor.authorRen, Qing Dao Er Jien_US
dc.contributor.authorShi, Baoen_US
dc.contributor.authorWu, Nier E.en_US
dc.contributor.authorLu, Minen_US
dc.contributor.authorLiu, Naen_US
dc.contributor.authorZhuang, Xu Feien_US
dc.contributor.authorXu, Xuan Xuanen_US
dc.contributor.authorWang, Lien_US
dc.contributor.authorDai, Ling Jieen_US
dc.contributor.authorYao, Miao Miaoen_US
dc.contributor.authorLi, Xiao Meien_US
dc.contributor.editorChaine, Raphaëlleen_US
dc.contributor.editorDeng, Zhigangen_US
dc.contributor.editorKim, Min H.en_US
dc.date.accessioned2023-10-09T07:42:54Z
dc.date.available2023-10-09T07:42:54Z
dc.date.issued2023
dc.description.abstractDrop type technique, as a method that can effectively regulate the co-adaptations and prediction ability of neural network units, is widely used in model parameter optimization to reduce overfitting problems. However, low resource image classification faces serious overfitting problems, and the data sparsity problem weakens or even disappears the effectiveness of most regularization methods. This paper is inspired by the value iteration strategy and attempts a Drop type method based on Metcalfe's law, named Metcalfe-Drop. The experimental results indicate that using Metcalfe-Drop technique as a basis to determine parameter sharing is more effective than randomly controlling neurons according to a certain probability. Our code is available at https://gitee.com/giteetu/metcalfe-drop.git.en_US
dc.description.sectionheadersPosters
dc.description.seriesinformationPacific Graphics Short Papers and Posters
dc.identifier.doi10.2312/pg.20231281
dc.identifier.isbn978-3-03868-234-9
dc.identifier.pages111-112
dc.identifier.pages2 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20231281
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/pg20231281
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies -> Image processing; Neural networks; Image representations
dc.subjectComputing methodologies
dc.subjectImage processing
dc.subjectNeural networks
dc.subjectImage representations
dc.titleA Simple Stochastic Regularization Technique for Avoiding Overfitting in Low Resource Image Classificationen_US
Files
Original bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
111-112.pdf
Size:
214.46 KB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
conf1010_poster.pdf
Size:
950.58 KB
Format:
Adobe Portable Document Format
Download
Collections
PG2023 Short Papers and Posters