45 citations · 86 across the 13 of their papers we have counts for
6 papers · 1 filter
Primate vision reveals a missing principle for robust dynamic AI
Matteo Dunnhofer, Christian Micheloni, Kohitij Kar
How does an intelligent visual system combine what objects look like with how they move while remaining robust as appearance changes? We addressed this question by comparing human…
CPUBone: Efficient Vision Backbone Design for Devices with Low Parallelization Capabilities
Moritz Nottebaum, Matteo Dunnhofer, Christian Micheloni
Recent research on vision backbone architectures has predominantly focused on optimizing efficiency for hardware platforms with high parallel processing capabilities. This category…
The macaque IT cortex but not current artificial vision networks encode object position in perceptually aligned coordinates
Elizaveta Yakubovskaya, Hamidreza Ramezanpour, Matteo Dunnhofer +1
Efficient interaction with the visual world requires not only accurate object identification but also precise localization of objects in space. While spatial ("where") processing h…
Beyond MACs: Hardware Efficient Architecture Design for Vision Backbones
Moritz Nottebaum, Matteo Dunnhofer, Christian Micheloni
Vision backbone networks play a central role in modern computer vision. Enhancing their efficiency directly benefits a wide range of downstream applications. To measure efficiency,…
Modeling Dynamic Computations in the Primate Ventral Visual Stream
Matteo Dunnhofer, Maren Wehrheim, Hamidreza Ramezanpour +2
A major goal of computational neuroscience has been to explain how the primate ventral visual stream (VVS) transforms visual input into temporally evolving neural representations t…
Better, But Not Sufficient: Testing Video ANNs Against Macaque IT Dynamics
Matteo Dunnhofer, Christian Micheloni, Kohitij Kar
Feedforward artificial neural networks (ANNs) trained on static images remain the dominant models of the the primate ventral visual stream, yet they are intrinsically limited to st…