Are deep neural networks adequate behavioral models of human visual perception?

FA Wichmann, R Geirhos - Annual Review of Vision Science, 2023 - annualreviews.org
Deep neural networks (DNNs) are machine learning algorithms that have revolutionized
computer vision due to their remarkable successes in tasks like object classification and …

Deep problems with neural network models of human vision

JS Bowers, G Malhotra, M Dujmović… - Behavioral and Brain …, 2023 - cambridge.org
Deep neural networks (DNNs) have had extraordinary successes in classifying
photographic images of objects and are often described as the best models of biological …

Getting aligned on representational alignment

I Sucholutsky, L Muttenthaler, A Weller, A Peng… - ar** in deep neural networks
V Biscione, JS Bowers - Computational Brain & Behavior, 2023 - Springer
Gestalt psychologists have identified a range of conditions in which humans organize
elements of a scene into a group or whole, and perceptual grou** principles play an …

Human shape representations are not an emergent property of learning to classify objects.

G Malhotra, M Dujmović, J Hummel… - Journal of Experimental …, 2023 - psycnet.apa.org
Humans are particularly sensitive to relationships between parts of objects. It remains
unclear why this is. One hypothesis is that relational features are highly diagnostic of object …

Learning online visual invariances for novel objects via supervised and self-supervised training

V Biscione, JS Bowers - Neural Networks, 2022 - Elsevier
Humans can identify objects following various spatial transformations such as scale and
viewpoint. This extends to novel objects, after a single presentation at a single pose …

Shape-selective processing in deep networks: integrating the evidence on perceptual integration

C Jarvers, H Neumann - Frontiers in Computer Science, 2023 - frontiersin.org
Understanding how deep neural networks resemble or differ from human vision becomes
increasingly important with their widespread use in Computer Vision and as models in …

Teaching deep networks to see shape: Lessons from a simplified visual world

C Jarvers, H Neumann - PLOS Computational Biology, 2024 - journals.plos.org
Deep neural networks have been remarkably successful as models of the primate visual
system. One crucial problem is that they fail to account for the strong shape-dependence of …