Arne Nix — accepted AI-conference papers

2023

Energy Guided Diffusion for Generating Neurally Exciting Images

Paweł A. Pierzchlewicz, Konstantin Friedrich Willeke, Arne Nix, Pavithra Elumalai, Kelli Restivo, Tori Shinn +6

NeurIPS 2023poster

In recent years, most exciting inputs (MEIs) synthesized from encoding models of neuronal activity have become an established method for studying tuning properties of biological and artificial visual systems. However, as we move up the visual hierarchy, the complexity of neuronal computations in…

Cited by 17 Source ↗PDF ↗code ↗Scholar ↗

2022

Can Functional Transfer Methods Capture Simple Inductive Biases?

Arne Nix, Suhas Shrinivasan, Edgar Y. Walker, Fabian Sinz

AISTATS 2022poster

Transferring knowledge embedded in trained neural networks is a core problem in areas like model compression and continual learning. Among knowledge transfer approaches, functional transfer methods such as knowledge distillation and representational distance learning are particularly promising, sinc…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2021

Towards robust vision by multi-task learning on monkey visual cortex

Shahd Safarani, Arne Nix, Konstantin Friedrich Willeke, Santiago A Cadena, Kelli Restivo, George Denfield +2

NeurIPS 2021poster

Deep neural networks set the state-of-the-art across many tasks in computer vision, but their generalization ability to simple image distortions is surprisingly fragile. In contrast, the mammalian visual system is robust to a wide range of perturbations. Recent work suggests that this generalization…

Cited by 53 Source ↗PDF ↗code ↗Scholar ↗