SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation

Mucong Ding, Bang An, Yuancheng Xu, Anirudh Satheesh, Furong Huang

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Data Augmentation, Learnable Augmentation, Bilevel Optimization

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We introduce SAFLEX, a bilevel optimization method for data augmentation, achieving promising results across multiple data types and tasks and seamlessly integrating with existing augmentation techniques.

Abstract: Data augmentation, a cornerstone technique in deep learning, is crucial in enhancing model performance, especially with scarce labeled data. While traditional techniques are effective, their reliance on hand-crafted methods limits their applicability across diverse data types and tasks. Although modern learnable augmentation methods offer increased adaptability, they are computationally expensive and challenging to incorporate within prevalent augmentation workflows. In this work, we present a novel, efficient method for data augmentation, effectively bridging the gap between existing augmentation strategies and emerging datasets and learning tasks. We introduce SAFLEX (Self-Adaptive Augmentation via Feature Label EXtrapolation), which learns the sample weights and soft labels of augmented samples provided by any given upstream augmentation pipeline, using a specifically designed efficient bilevel optimization algorithm. Remarkably, SAFLEX effectively reduces the noise and label errors of the upstream augmentation pipeline with a marginal computational cost. As a versatile module, SAFLEX excels across diverse datasets, including natural and medical images and tabular data, showcasing its prowess in few-shot learning and out-of-distribution generalization. SAFLEX seamlessly integrates with common augmentation strategies like RandAug, CutMix, and those from large pre-trained generative models like stable diffusion and is also compatible with frameworks such as CLIP's fine-tuning. Our findings highlight the potential to adapt existing augmentation pipelines for new data types and tasks, signaling a move towards more adaptable and resilient training frameworks.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 3847