Do Invariances in Deep Neural Networks Align with Human Perception?. (arXiv:2111.14726v3 [cs.CV] UPDATED)

An evaluation criterion for safe and trustworthy deep learning is how well
the invariances captured by representations of deep neural networks (DNNs) are
shared with humans. We identify challenges in measuring these invariances.
Prior works used gradient-based methods to generate \textit{identically
represented inputs} (IRIs), \ie, inputs which have identical representations
(on a given layer) of a neural network, and thus capture invariances of a given
network. One necessary criterion for a network's invariances to align with
human perception is for …

arxiv cv human networks neural networks perception