Topographic Neural Networks Help computer vision Like a Human. Really!

Food for thought! Does computer vision have to mimic human vision? I don't think so!

Maybe the claimed better energy efficiency is a distinctive feature of this model.

"AI-vision models have improved dramatically over the past decade. Yet these gains have led to neural networks that, though effective, don’t share many characteristics with human vision. For example, convolutional neural networks (CNN) are often better at noticing texture, while humans respond more strongly to shapes.

A paper recently published ... has partially addressed that gap. It describes a novel All-Topographic Neural Network (All-TNN) that, when trained on natural images, developed an organized, specialized structure more like human vision. The All-TNN better mimicked human spatial biases, like expecting to see an airplane closer to the top of an image than the bottom, and operated on a significantly lower energy budget than other neural networks used for machine vision. ..."

From the abstract:

"A prominent feature of the primate visual system is its topographic organization. For understanding its origins, its computational role and its behavioural implications, computational models are of central importance.

Yet, vision is commonly modelled using convolutional neural networks, which are hard-wired to learn identical features across space and thus lack topography. Here we overcome this limitation by introducing all-topographic neural networks (All-TNNs). All-TNNs develop several features reminiscent of primate topography, including smooth orientation and category selectivity maps, and enhanced processing of regions with task-relevant information.

In addition, All-TNNs operate on a low energy budget, suggesting a metabolic benefit of smooth topographic organization. To test our model against behaviour, we collected a dataset of human spatial biases in object recognition and found that All-TNNs significantly outperform control models. All-TNNs thereby offer a promising candidate for modelling primate visual topography and its role in downstream behaviour."

Topographic Neural Networks Help AI See Like a Human - IEEE Spectrum "Topographic neural networks develop familiar spatial biases"

End-to-end topographic networks as models of cortical map formation and human visual behaviour (open access)

Fig. 1: All-TNNs.