4 papers
Keypoint Counting Classifiers: Turning Vision Transformers into Self-Explainable Models Without Training
Kristoffer Wickstrøm, Teresa Dorszewski, Siyan Chen +3
Current approaches for designing self-explainable models (SEMs) require complicated training procedures and specific architectures which makes them impractical. With the advance of…
Mammo-CLIP Dissect: A Framework for Analysing Mammography Concepts in Vision-Language Models
Suaiba Amina Salahuddin, Teresa Dorszewski, Marit Almenning Martiniussen +7
Understanding what deep learning (DL) models learn is essential for the safe deployment of artificial intelligence (AI) in clinical settings. While previous work has focused on pix…
From Colors to Classes: Emergence of Concepts in Vision Transformers
Teresa Dorszewski, Lenka Tětková, Robert Jenssen +2
Vision Transformers (ViTs) are increasingly utilized in various computer vision tasks due to their powerful representation capabilities. However, it remains understudied how ViTs p…
Connecting Concept Convexity and Human-Machine Alignment in Deep Neural Networks
Teresa Dorszewski, Lenka Tětková, Lorenz Linhardt +1
Understanding how neural networks align with human cognitive processes is a crucial step toward developing more interpretable and reliable AI systems. Motivated by theories of huma…