Log In Sign Up

Is the U-Net Directional-Relationship Aware?

by   Mateus Riva, et al.

CNNs are often assumed to be capable of using contextual information about distinct objects (such as their directional relations) inside their receptive field. However, the nature and limits of this capacity has never been explored in full. We explore a specific type of relationship – directional – using a standard U-Net trained to optimize a cross-entropy loss function for segmentation. We train this network on a pretext segmentation task requiring directional relation reasoning for success and state that, with enough data and a sufficiently large receptive field, it succeeds to learn the proposed task. We further explore what the network has learned by analysing scenarios where the directional relationships are perturbed, and show that the network has learned to reason using these relationships.


page 2

page 3

page 4


Neural Ordinary Differential Equations for Semantic Segmentation of Individual Colon Glands

Automated medical image segmentation plays a key role in quantitative re...

BiCANet: Bi-directional Contextual Aggregating Network for Image Semantic Segmentation

Exploring contextual information in convolution neural networks (CNNs) h...

Contextual Two-Stage U-Nets for Robust Pulmonary Lobe Segmentation in CT Scans of COVID-19 and COPD Patients

Pulmonary lobe segmentation in computed tomography scans is essential fo...

Investigations of the Influences of a CNN's Receptive Field on Segmentation of Subnuclei of Bilateral Amygdalae

Segmentation of objects with various sizes is relatively less explored i...

First arrival picking using U-net with Lovasz loss and nearest point picking method

We proposed a robust segmentation and picking workflow to solve the firs...

Directional Graph Networks

In order to overcome the expressive limitations of graph neural networks...

Complementary Bi-directional Feature Compression for Indoor 360° Semantic Segmentation with Self-distillation

Recently, horizontal representation-based panoramic semantic segmentatio...