Timezone: »

 
Conditional Diffusion Replay for Continual Learning in Medical Settings
Yewon Byun · Saurabh Garg · Sanket Vaibhav Mehta · Praveer Singh · Jayashree Kalpathy-cramer · Bryan Wilder · Zachary Lipton

@
in Challenges in Deployable Generative AI »
Event URL: https://openreview.net/forum?id=avmAZiWarU »

Episodic replay methods, which store and replay past data, have proven effective for handling distribution shifts in continual learning. However, due to regulatory and privacy concerns for data sharing, their applicability can be limited, especially in healthcare.In this work, we advance the state of art,focusing our inquiry on two novel benchmarks for domain incremental continual learning: diabetic retinopathy severity classification and dermoscopy skin lesion detection.First, we demonstrate the poor forward and backward transferability of simple baselines. Then, to overcome these challenges, we propose a novel method called conditional diffusion replay. By leveraging a text-to-image diffusion model for synthetic data generation, our approach effectively preservesperformance on previously encountered domainswhile adapting to new ones.We observe that compared to standard sequential fine-tuning, our conditional diffusion replay method improves average AUC by up to 6.2 points and 3.3 points for the skin lesions and diabetic retinopathy benchmarks, respectively.

Keywords: Generative Models · continual learning · Medical Imaging · distribution shift

Author Information

Yewon Byun (Machine Learning Department, School of Computer Science)
Saurabh Garg (Carnegie Mellon University)
Sanket Vaibhav Mehta (Carnegie Mellon University)
Praveer Singh (University of Colorado School of Medicine)
Jayashree Kalpathy-cramer (MGH)
Bryan Wilder (Carnegie Mellon University)
Zachary Lipton (CMU & Abridge)

More from the Same Authors