SLACK: Stable Learning of Augmentations with Cold-start and KL regularization

CVPR 2023

Juliette Marrie1,2, Michael Arbel1Diane Larlus1,2, Julien Mairal1

1 Univ.\ Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK            2 NAVER LABS Europe


Data augmentation is known to improve the generalization capabilities of neural networks, provided that the set of transformations is chosen with care, a selection  often performed manually. Automatic data augmentation aims at automating this process. However, most recent approaches still rely on some prior information; they start from a small pool of manually-selected default transformations that are either used to pretrain the network or forced to be part of the policy learned by the automatic data augmentation algorithm. In this paper, we propose to directly learn the augmentation policy without leveraging such prior knowledge. The resulting bilevel optimization problem becomes more challenging due to the larger search space and the inherent instability of bilevel optimization algorithms. To mitigate these issues (i) we follow a successive cold-start strategy with a Kullback-Leibler regularization, and (ii) we parameterize magnitudes as continuous distributions. Our approach leads to competitive results on standard benchmarks despite a more challenging setting, and generalizes beyond natural images.

Visualization of learned policies


For different domains of the DomainNet dataset (one per line), we show an image from that domain (left) and that image transformed using the three most likely (middle) and the three least likely (right) augmentations for that domain, as estimated by SLACK


If you find our paper or pretrained models useful for your research, please consider citing us.


     author = {Marrie, Juliette and Arbel, Michael and Larlus, Diane and Mairal, Julien},
     title = {SLACK: Stable Learning of Augmentations with Cold-start and KL regularization},
     booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
     month = {June},
     year = {2023}

This web site uses cookies for the site search, to display videos and for aggregate site analytics.

Learn more about these cookies in our privacy notice.


Cookie settings

You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.

FunctionalThis website uses functional cookies which are required for the search function to work and to apply for jobs and internships.

AnalyticalOur website uses analytical cookies to make it possible to analyse our website and optimize its usability.

Social mediaOur website places social media cookies to show YouTube and Vimeo videos. Cookies placed by these sites may track your personal data.