GridMix: Strong regularization through local context mapping

Kyungjune Baek, Duhyeon Bang, Hyunjung Shim

Research output: Contribution to journalArticle


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.

Original languageEnglish
Article number107594
JournalPattern Recognition
Publication statusPublished - 2021 Jan

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'GridMix: Strong regularization through local context mapping'. Together they form a unique fingerprint.

  • Cite this