Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity
arXiv:2102.03065
Abstract
While deep neural networks show great performance on fitting to the training distribution, improving the networks' generalization performance to the test distribution and robustness to the sensitivity to input perturbations still remain as a challenge. Although a number of mixup based augmentation strategies have been proposed to partially address them, it remains unclear as to how to best utilize the supervisory signal within each input data for mixup from the optimization perspective. We propose a new perspective on batch mixup and formulate the optimal construction of a batch of mixup data maximizing the data saliency measure of each individual mixup data and encouraging the supermodular diversity among the constructed mixup data. This leads to a novel discrete optimization problem minimizing the difference between submodular functions. We also propose an efficient modular approximation based iterative submodular minimization algorithm for efficient mixup computation per each minibatch suitable for minibatch based neural network training. Our experiments show the proposed method achieves the state of the art generalization, calibration, and weakly supervised localization results compared to other mixup methods. The source code is available at https://github.com/snu-mllab/Co-Mixup.
arXiv commentPublished at ICLR 2021 (Oral)
References in corpus (9)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Wide Residual Networks
- CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
- A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets
- Algorithms for Approximate Minimization of the Difference Between Submodular Functions, with Applications
- Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup
- Maximization of Approximately Submodular Functions
- Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator