2 papers
cs.CV2024
Understanding Inhibition Through Maximally Tense Images
Chris Hamblin, Srijani Saha, Talia Konkle +1
We address the functional role of 'feature inhibition' in vision models; that is, what are the mechanisms by which a neural network ensures images do not express a given feature? W…
cs.CV2024
Feature Accentuation: Revealing 'What' Features Respond to in Natural Images
Chris Hamblin, Thomas Fel, Srijani Saha +2
Efforts to decode neural network vision models necessitate a comprehensive grasp of both the spatial and semantic facets governing feature responses within images. Most research ha…