51 citations · 51 across the 6 of their papers we have counts for
7 papers
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…
RefTr: Recurrent Refinement of Confluent Trajectories for 3D Vascular Tree Centerlines
Roman Naeem, David Hagerman, Jennifer Alvén +1
Tubular tree structures such as blood vessels and lung airways are central to many clinical tasks, including diagnosis, treatment planning, and surgical navigation. Accurate center…
Trexplorer Super: Topologically Correct Centerline Tree Tracking of Tubular Objects in CT Volumes
Roman Naeem, David Hagerman, Jennifer Alvén +2
Tubular tree structures, such as blood vessels and airways, are essential in human anatomy and accurately tracking them while preserving their topology is crucial for various downs…
Optimizing Gene-Based Testing for Antibiotic Resistance Prediction
David Hagerman, Anna Johnning, Roman Naeem +3
Antibiotic Resistance (AR) is a critical global health challenge that necessitates the development of cost-effective, efficient, and accurate diagnostic tools. Given the genetic ba…
Masked Autoencoder for Self-Supervised Pre-training on Lidar Point Clouds
Georg Hess, Johan Jaxing, Elias Svensson +3
Masked autoencoding has become a successful pretraining paradigm for Transformer models for text, images, and, recently, point clouds. Raw automotive datasets are suitable candidat…