activity
20202026
most citedModDrop++: A Dynamic Filter Network with Intra-subject Co-training for Multiple Sclerosis Lesion Segmentation with Missing Modalities

4 citations · 10 across the 7 of their papers we have counts for

collaborators
Showing 2025Show all

1 paper · 1 filter

cs.CV2025

Spatially-Adaptive Gradient Re-parameterization for 3D Large Kernel Optimization

Ho Hin Lee, Quan Liu, Shunxing Bao +2

Large kernel convolutions offer a scalable alternative to vision transformers for high-resolution 3D volumetric analysis, yet naively increasing kernel size often leads to optimiza…