Higher-Resolution Microscopy Can Make Deep Learning Worse by Shrinking a CNN's Physical Receptive Field

bravo_abad · x · 2026-09-23

From an AI-for-Science newsletter: Ferreira et al. show that when microscopy images become too high-resolution, a CNN's fixed receptive field covers a smaller physical region of the sample, hurting performance. The takeaway: match the experiment's resolution to the model's receptive field rather than defaulting to maximum resolution data.

Related event: Higher Microscopy Resolution Can Hurt CNN Segmentation, Study Finds(2 posts)→

Original post →

More from Research

Research channel →