Model editing for distribution shifts in uranium oxide morphological analysis

Autor:	Brown, Davis, Nizinski, Cody, Shapiro, Madelyn, Fallon, Corey, Yin, Tianzhixi, Kvinge, Henry, Tu, Jonathan H.
Rok vydání:	2024
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	Deep learning still struggles with certain kinds of scientific data. Notably, pretraining data may not provide coverage of relevant distribution shifts (e.g., shifts induced via the use of different measurement instruments). We consider deep learning models trained to classify the synthesis conditions of uranium ore concentrates (UOCs) and show that model editing is particularly effective for improving generalization to distribution shifts common in this domain. In particular, model editing outperforms finetuning on two curated datasets comprising of micrographs taken of U$_{3}$O$_{8}$ aged in humidity chambers and micrographs acquired with different scanning electron microscopes, respectively. Comment: Presented at CV4MS @ CVPR 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2407.15756 Zobrazit plný text záznamu View this record from Arxiv