6 papers
FiRe: Fixed-Noise Refinement for Visual Counterfactual Explanations
Yan Zeng, Changlu Guo, Oskar Kristoffersen +3
Visual counterfactual explanations aim to change classifier decisions through realistic and localized edits while preserving decision-irrelevant content. Existing DDPM-based method…
MMLANDMARKS: a Cross-View Instance-Level Benchmark for Geo-Spatial Understanding
Oskar Kristoffersen, Alba Reinders Sánchez, Morten Rieger Hannemose +2
Geo-spatial analysis of our world benefits from a multimodal approach, as every single geographic location can be described in numerous ways (images from various viewpoints, textua…
MaskDiME: Adaptive Masked Diffusion for Precise and Efficient Visual Counterfactual Explanations
Changlu Guo, Anders Nymark Christensen, Anders Bjorholm Dahl +1
Visual counterfactual explanations aim to reveal the minimal semantic modifications that can alter a model's prediction, providing causal and interpretable insights into deep neura…
Learning to Build Shapes by Extrusion
Thor Vestergaard Christiansen, Karran Pandey, Alba Reinders +3
We introduce Text Encoded Extrusions (TEE), a text-based representation that expresses mesh construction as sequences of face extrusions rather than polygon lists, and a method for…
SA-UNetv2: Rethinking Spatial Attention U-Net for Retinal Vessel Segmentation
Changlu Guo, Anders Nymark Christensen, Anders Bjorholm Dahl +2
Retinal vessel segmentation is essential for early diagnosis of diseases such as diabetic retinopathy, hypertension, and neurodegenerative disorders. Although SA-UNet introduces sp…
Med-Art: Diffusion Transformer for 2D Medical Text-to-Image Generation
Changlu Guo, Anders Nymark Christensen, Morten Rieger Hannemose
Text-to-image generative models have achieved remarkable breakthroughs in recent years. However, their application in medical image generation still faces significant challenges, i…