Approximation of dilation-based spatial relations to add structural constraints in neural networks

02/22/2021
by   Mateus Riva, et al.
0

Spatial relations between objects in an image have proved useful for structural object recognition. Structural constraints can act as regularization in neural network training, improving generalization capability with small datasets. Several relations can be modeled as a morphological dilation of a reference object with a structuring element representing the semantics of the relation, from which the degree of satisfaction of the relation between another object and the reference object can be derived. However, dilation is not differentiable, requiring an approximation to be used in the context of gradient-descent training of a network. We propose to approximate dilations using convolutions based on a kernel equal to the structuring element. We show that the proposed approximation, even if slightly less accurate than previous approximations, is definitely faster to compute and therefore more suitable for computationally intensive neural network applications.

READ FULL TEXT

page 4

page 8

page 9

research
02/02/2022

Approximate Bisimulation Relations for Neural Networks and Application to Assured Neural Network Compression

In this paper, we propose a concept of approximate bisimulation relation...
research
11/30/2017

Relation Networks for Object Detection

Although it is well believed for years that modeling relations between o...
research
09/29/2018

Knowledge-guided Semantic Computing Network

It is very useful to integrate human knowledge and experience into tradi...
research
07/04/2017

Optimization Beyond the Convolution: Generalizing Spatial Relations with End-to-End Metric Learning

To operate intelligently in domestic environments, robots require the ab...
research
02/01/2023

Gradient Descent in Neural Networks as Sequential Learning in RKBS

The study of Neural Tangent Kernels (NTKs) has provided much needed insi...
research
01/23/2020

Learning Object Placements For Relational Instructions by Hallucinating Scene Representations

Robots coexisting with humans in their environment and performing servic...

Please sign up or login with your details

Forgot password? Click here to reset