SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.03065 · ICLR · 2021

Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity

Jang-Hyun Kim, Wonho Choo, Hyun Song, Hosan Jeong, Hyun Oh

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2102.03065")
get_code_for_paper("2102.03065")
have("2102.03065")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2102.03065.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2102.03065.svg)](https://syntology.ai/paper/2102.03065)

Connect an agent — have() is free.