Marin Dujmović

This study shows that supervised CNNs do not develop human-like sensitivity to relational shape changes when classifying objects.

This paper investigates shape-bias in humans and CNNs, finding that humans rely on shape despite non-shape features being more diagnostic, while CNNs adapt to predictive features.

The paper identifies issues with Representational Similarity Analysis (RSA) when comparing neural systems, showing how confounds in stimuli can lead to misleading similarity scores between different systems.

This study reanalyzes adversarial image data to show weak and variable agreement between humans and DCNNs, challenging the claim that DCNNs are good models of human vision.