GridMix: Strong regularization through local context mapping

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.

Automated summary

This paper introduces a method called GridMix for improving network generalization by predicting patch-level labels and utilizing grid-based mixing for local data augmentation. Experimental results show that GridMix outperforms state-of-the-art techniques in classification and adversarial robustness, achieving comparable performance in weakly supervised object localization.