DeepAI AI Chat
Log In Sign Up

KerCNNs: biologically inspired lateral connections for classification of corrupted images

by   Noemi Montobbio, et al.

The state of the art in many computer vision tasks is represented by Convolutional Neural Networks (CNNs). Although their hierarchical organization and local feature extraction are inspired by the structure of primate visual systems, the lack of lateral connections in such architectures critically distinguishes their analysis from biological object processing. The idea of enriching CNNs with recurrent lateral connections of convolutional type has been put into practice in recent years, in the form of learned recurrent kernels with no geometrical constraints. In the present work, we introduce biologically plausible lateral kernels encoding a notion of correlation between the feedforward filters of a CNN: at each layer, the associated kernel acts as a transition kernel on the space of activations. The lateral kernels are defined in terms of the filters, thus providing a parameter-free approach to assess the geometry of horizontal connections based on the feedforward structure. We then test this new architecture, which we call KerCNN, on a generalization task related to global shape analysis and pattern completion: once trained for performing basic image classification, the network is evaluated on corrupted testing images. The image perturbations examined are designed to undermine the recognition of the images via local features, thus requiring an integration of context information - which in biological vision is critically linked to lateral connectivity. Our KerCNNs turn out to be far more stable than CNNs and recurrent CNNs to such degradations, thus validating this biologically inspired approach to reinforce object recognition under challenging conditions.


page 17

page 29

page 31


Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future

Convolutional neural networks (CNNs) were inspired by early findings in ...

Biologically Inspired Semantic Lateral Connectivity for Convolutional Neural Networks

Lateral connections play an important role for sensory processing in vis...

Convolutional Neural Networks with Gated Recurrent Connections

The convolutional neural network (CNN) has become a basic model for solv...

Perception Over Time: Temporal Dynamics for Robust Image Understanding

While deep learning surpasses human-level performance in narrow and spec...

Emergence of Lie symmetries in functional architectures learned by CNNs

In this paper we study the spontaneous development of symmetries in the ...

LGN-CNN: a biologically inspired CNN architecture

In this paper we introduce a biologically inspired CNN architecture that...