← Search

Till Speicher

2 accepted papers

2023

Diffused Redundancy in Pre-trained Representations

NeurIPS 2023poster

Representations learned by pre-training a neural network on a large dataset are increasingly used successfully to perform a variety of downstream tasks. In this work, we take a closer look at how features are encoded in such pre-trained representations. We find that learned representations in a give…

2022

Measuring Representational Robustness of Neural Networks Through Shared Invariances

ICML 2022oral

A major challenge in studying robustness in deep learning is defining the set of “meaningless” perturbations to which a given Neural Network (NN) should be invariant. Most work on robustness implicitly uses a human as the reference model to define such perturbations. Our work offers a new view on ro…