GridMix: Strong regularization through local context mapping

Cited 14 time in webofscience Cited 0 time in scopus
  • Hit : 193
  • Download : 0
Recently developed regularization techniques improve the networks generalization by only considering the global context. Therefore, the network tends to focus on a few most discriminative subregions of an image for prediction accuracy, leading the network being sensitive to unseen or noisy data. To address this disadvantage, we introduce the concept of local context mapping by predicting patch-level labels and combine it with a method of local data augmentation by grid-based mixing, called GridMix. Through our analysis of intermediate representations, we show that our GridMix can effectively regularize the network model. Finally, our evaluation results indicate that GridMix outperforms state-of-the-art techniques in classification and adversarial robustness, and it achieves a comparable performance in weakly supervised object localization. (C) 2020 Elsevier Ltd. All rights reserved.
Publisher
ELSEVIER SCI LTD
Issue Date
2021-01
Language
English
Article Type
Article
Citation

PATTERN RECOGNITION, v.109

ISSN
0031-3203
DOI
10.1016/j.patcog.2020.107594
URI
http://hdl.handle.net/10203/297168
Appears in Collection
AI-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 14 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0