1 code implementation • 8 Jun 2024 • Chris Hamblin, Srijani Saha, Talia Konkle, George Alvarez
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?
no code implementations • 15 Feb 2024 • Chris Hamblin, Thomas Fel, Srijani Saha, Talia Konkle, George Alvarez
Most research has primarily centered around attribution methods, which provide explanations in the form of heatmaps, showing where the model directs its attention for a given feature.