AFFMAE brings 5x faster high-res vision pretraining to desktop hardware, at ECCV 2026

CSProfKGD · x · 2026-09-07

Researchers present AFFMAE at ECCV 2026: a masking-friendly hierarchical pretraining framework built on AutoFocusFormer's adaptive, off-grid token merging, aimed at high-resolution microscopy segmentation.

Key points:

Original post →

More from Infra

Infra channel →