Topic: identity-preserving transformations

The brain must recognize objects in the face of identity-preserving transformations such as changes in lighting, position, and orientation. However, to achieve general purpose geometric reasoning these view transformations should also be represented in neural codes. A natural strategy to encode both the identity of an object and its view is to utilize an equivariant code, where the neural representation transforms in a manner consistent with the transformations to the inputs, and consistent across objects. A classic example of such a code is given by an intermediate layer of a convolutional ne

Object vision relies on the ability to tolerate identity-preserving transformations, such as scaling, translation, and rotation of visual objects. Even larger transformations can be achieved when a visual pattern emerges from second-order (texture) cues or by configural arrangements of local features constructing a global (Gestalt) figure. While humans generalize across such transformations, it remains unclear whether lower mammals, such as rodents, share with us this ability. Recent studies have shown that rats can recognize objects despite identity-preserving transformations, but little is k