Harmonizing the Object Recognition Strategies of Deep Neural Networks with Humans
Thomas Fel, Iván Felipe, Drew Linsley, T. Serre
Abstract
. We rectify this growing issue with our neural harmonizer: a general-purpose training routine that both aligns DNN and human visual strategies and improves categorization accuracy. Our work represents the first demonstration that the scaling laws [1-3] that are guiding the design of DNNs today have also produced worse models of human vision. We release our code and data at https://serre-lab.github.io/Harmonization to help the field build more human-like DNNs.
Topics & Concepts
CategorizationComputer scienceArtificial intelligenceDeep neural networksCognitive neuroscience of visual object recognitionObject (grammar)HarmonizationMachine learningArtificial neural networkPhysicsAcousticsVisual Attention and Saliency DetectionFace Recognition and PerceptionVisual perception and processing mechanisms