Symmetry Perception by Deep Networks: Inadequacy of Feed-Forward Architectures and Improvements with Recurrent Connections

12/08/2021
by   Shobhita Sundaram, et al.
0

Symmetry is omnipresent in nature and perceived by the visual system of many species, as it facilitates detecting ecologically important classes of objects in our environment. Symmetry perception requires abstraction of non-local spatial dependencies between image regions, and its underlying neural mechanisms remain elusive. In this paper, we evaluate Deep Neural Network (DNN) architectures on the task of learning symmetry perception from examples. We demonstrate that feed-forward DNNs that excel at modelling human performance on object recognition tasks, are unable to acquire a general notion of symmetry. This is the case even when the DNNs are architected to capture non-local spatial dependencies, such as through `dilated' convolutions and the recently introduced `transformers' design. By contrast, we find that recurrent architectures are capable of learning to perceive symmetry by decomposing the non-local spatial dependencies into a sequence of local operations, that are reusable for novel images. These results suggest that recurrent connections likely play an important role in symmetry perception in artificial systems, and possibly, biological ones too.

READ FULL TEXT

page 3

page 5

page 6

page 9

page 10

page 12

research
04/16/2019

Learning a Gauge Symmetry with Neural Networks

We explore the capacity of neural networks to detect a symmetry with com...
research
12/22/2017

Learning in the Machine: the Symmetries of the Deep Learning Channel

In a physical neural system, learning rules must be local both in space ...
research
02/28/2020

Two Routes to Scalable Credit Assignment without Weight Symmetry

The neural plausibility of backpropagation has long been disputed, prima...
research
08/25/2017

Identifying Mirror Symmetry Density with Delay in Spiking Neural Networks

The ability to rapidly identify symmetry and anti-symmetry is an essenti...
research
06/08/2017

CortexNet: a Generic Network Family for Robust Visual Temporal Representations

In the past five years we have observed the rise of incredibly well perf...
research
08/02/2018

Perception of Symmetries in Drawings of Graphs

Symmetry is an important factor in human perception in general, as well ...
research
08/26/2018

Affine Geometry, Visual Sensation, and Preference for Symmetry of Things in a Thing

Evolution and geometry generate complexity in similar ways. Evolution dr...

Please sign up or login with your details

Forgot password? Click here to reset