Invariance properties of the human visual system in one-shot learning

Abstract

This work first characterizes human invariant recognition in one-shot learning. By using novel stimuli, we address the question whether invariance to transformation emerges from experience and memorization of templates or from the brain instantly computing invariant representation. Our psychophysical experimental results suggest that human vision produces a representation that is robust in terms of scale change, but it needs experience for translation-invariance. Next, we examine the implication of the experimental data with regards to computational modeling. In particular, we confirm that the eccentricity-dependent model [16], where scale-invariance is built in the underlying architecture, reproduces the human data closely.