Associative Memories in the Feature Space

arXiv:2402.10814v1 Announce Type: new
Abstract: An autoassociative memory model is a function that, given a set of data points, takes as input an arbitrary vector and outputs the most similar data point from the memorized set. However, popular memory models fail to retrieve images even when the corruption is mild and easy to detect for a human evaluator. This is because similarities are evaluated in the raw pixel space, which does not contain any semantic information about the images. This …

abstract arxiv corruption cs.cv cs.lg data easy feature function images memories memory popular set space type vector