4 papers
MedPruner: Training-Free Hierarchical Token Pruning for Efficient 3D Medical Image Understanding in Vision-Language Models
Shengyuan Liu, Zanting Ye, Yunrui Lin +6
While specialized Medical Vision-Language Models (VLMs) have achieved remarkable success in interpreting 2D and 3D medical modalities, their deployment for 3D volumetric data remai…
GPU Memory and Utilization Estimation for Training-Aware Resource Management: Opportunities and Limitations
Ehsan Yousefzadeh-Asl-Miandoab, Reza Karimzadeh, Danyal Yorulmaz +2
Collocating deep learning training tasks improves GPU utilization but risks resource contention, severe slowdowns, and out-of-memory (OOM) failures. Accurate memory estimation is e…
rNCA: Self-Repairing Segmentation Masks
Malte Silbernagel, Albert Alonso, Jens Petersen +3
Accurately predicting topologically correct masks remains a difficult task for general segmentation models, which often produce fragmented or disconnected outputs. Fixing these art…
Extremal Contours: Gradient-driven contours for compact visual attribution
Reza Karimzadeh, Albert Alonso, Frans Zdyb +2
Faithful yet compact explanations for vision models remain a challenge, as commonly used dense perturbation masks are often fragmented and overfitted, needing careful post-processi…