Skip to Main content Skip to Navigation
New interface
Conference papers

IS THE U-NET DIRECTIONAL-RELATIONSHIP AWARE?

Abstract : 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.
Document type :
Conference papers
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03715361
Contributor : Mateus Riva Connect in order to contact the contributor
Submitted on : Wednesday, July 6, 2022 - 12:38:30 PM
Last modification on : Tuesday, August 2, 2022 - 4:04:00 AM

File

ICIP___Is_the_U_Net_Directiona...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03715361, version 1

Citation

Mateus Riva, Pietro Gori, Florian Yger, Isabelle Bloch. IS THE U-NET DIRECTIONAL-RELATIONSHIP AWARE?. International Conference on Image Processing, Oct 2022, Bordeaux, France. ⟨hal-03715361⟩

Share

Metrics

Record views

186

Files downloads

8