# Direct Differentiable Augmentation Search

Source: [Direct Differentiable Augmentation Search](<https://www.sota2.com/research/paper/68fa6af51e209131cea2b5a2>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:37:16.577Z

Authors: Aoming Liu, Zehao Huang, Zhiwu Huang, Naiyan Wang

Published: 2021-04-09T10:02:24.000Z

## Abstract

Data augmentation has been an indispensable tool to improve the performance of deep neural networks, however the augmentation can hardly transfer among different tasks and datasets. Consequently, a recent trend is to adopt AutoML technique to learn proper augmentation policy without extensive hand-crafted tuning. In this paper, we propose an efficient differentiable search algorithm called Direct Differentiable Augmentation Search (DDAS). It exploits meta-learning with one-step gradient update and continuous relaxation to the expected training loss for efficient search. Our DDAS can achieve efficient augmentation search without relying on approximations such as Gumbel Softmax or second order gradient approximation. To further reduce the adverse effect of improper augmentations, we organize the search space into a two level hierarchy, in which we first decide whether to apply augmentation, and then determine the specific augmentation policy. On standard image classification benchmarks, our DDAS achieves state-of-the-art performance and efficiency tradeoff while reducing the search cost dramatically, e.g. 0.15 GPU hours for CIFAR-10. In addition, we also use DDAS to search augmentation for object detection task and achieve comparable performance with AutoAugment, while being 1000x faster.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2104.04282>)

[PDF](<https://arxiv.org/pdf/2104.04282.pdf>)
