51 citations · 51 across the 6 of their papers we have counts for
3 papers · 1 filter
BATS: Resource-Efficient Volumetric Segmentation with Boundary-Aware Mixed-Resolution Tokens
David Hagerman, Roman Naeem, Fredrik Kahl
Many high-performing volumetric segmentation models maintain dense multi-scale feature maps, leading to high activation memory and inference cost. We present BATS (Boundary-Aware T…
SwInception -- Local Attention Meets Convolutions
David Hagerman, Roman Naeem, Jakob Lindqvist +3
Sparse vision transformers have gained popularity as efficient encoders for medical volumetric segmentation, with Swin emerging as a prominent choice. Swin uses local attention to…
ARTA: Adaptive Mixed-Resolution Token Allocation for Efficient Dense Feature Extraction
David Hagerman, Roman Naeem, Erik Brorsson +2
We present ARTA, a mixed-resolution coarse-to-fine vision transformer for efficient dense feature extraction. Unlike models that begin with dense high-resolution (fine) tokens, ART…