Learning to Discount Transformations as the Computational Goal of Visual Cortex.” Presented at FGVC/CVPR 2011

them It has been long recognized that a key obstacle to achiev-ing human-level object recognition performance is the prob-lem of invariance [10]. The human visual system excels at factoring out the image transformations that distort ob-ject appearance under natural conditions. Models with a cortex-inspired architecture such as HMAX [9, 13] as well as nonbiological convolutional neural networks [5] are in-variant to translation (and in some cases scaling) by virtue of their wiring. The transformations to which this approach has been applied so far are generic transformations; a sin-gle example image of any object contains all the informa-tion needed to synthesize a new image of the tranformed object [15]. In a setting in which transformation invariance must be learned from visual experience (such as for a new