Papers › Direct Differentiable Augmentation Search

Direct Differentiable Augmentation Search

9 Apr 2021ICCV 2021 10arXiv:2104.04282archive 2025-07-28

Aoming Liu, Zehao Huang, Zhiwu Huang, Naiyan Wang

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

zxcvfd13502/ddas_code officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

AutoMLData AugmentationImage ClassificationMeta-LearningObject Detectionimage-classificationobject-detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AutoAugmentGumbel SoftmaxLSTMSigmoid ActivationSoftmaxTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections