Year: 2024
Type: preprint
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.
Source: arXiv (Cornell University)
Institution: University of Maryland, College Park
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: G1523888516, G4720003262, G4805816520, FAI: Toward Fair Decision Making and Resource Allocation with Application to AI-Assisted Graduate Admission and Degree Completion, G6098521345, G7437616762, TRUSTWORTHY REAL-TIME COMMUNICATIVE MULTI-AGENT REINFORCEMENT LEARNING FOR DECISION-MAKING IN UNSTABLE & ADVERSARIAL SYSTEMS, AUTONOMOUS DECISION-MAKING SYSTEMS UNDER (ADVERSARIAL) DISTRIBUTION SHIFTS: LEARNING TO ADAPT, GENERALIZE AND ROBUSTIFY, THE PURPOSE OF THIS AGREEMENT IS TO FUND RESEARCH SUPPORTING THE DEFENSE ADVANCED RESEARCH PROJECTS AGENCY DARPA GUARANTEEING AI ROBUSTNESS AGAINST DECEPTION GARD PROGRAM. THE TERM OF THE BASE PERIOD FOR THIS AGREEMENT COMMENCES ON THE EFFECTIVE DATE OF THE AWARD AND CONTINUES FOR TWELVE 12 MONTHS AFTER AWARD., G8876996369
OpenAlex ID: W4403884006