SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.06172 · ICLR · 2022

Deep AutoAugment

Shen Yan, Yu Zheng, Mi Zhang, Zhi Zhang

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 recent automated data augmentation methods lead to state-of-the-art results, their design spaces and the derived data augmentation strategies still incorporate strong human priors. In this work, instead of fixing a set of hand-picked default augmentations alongside the searched data augmentations, we propose a fully automated approach for data augmentation search named Deep AutoAugment (DeepAA). DeepAA progressively builds a multi-layer data augmentation pipeline from scratch by stacking augmentation layers one at a time until reaching convergence. For each augmentation layer, the policy is optimized to maximize the cosine similarity between the gradients of the original and augmented data along the direction with low variance. Our experiments show that even without default augmentations, we can learn an augmentation policy that achieves strong performance with that of previous works. Extensive ablation studies show that the regularized gradient matching is an effective search method for data augmentation policies.

For agents

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

get_harvested_code_for_paper("2203.06172")
get_code_for_paper("2203.06172")
have("2203.06172")

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

curl https://syntology.ai/api/ran/2203.06172.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.06172.svg)](https://syntology.ai/paper/2203.06172)

Connect an agent — have() is free.