English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Implicit scene segmentation in deeper convolutional neural networks

Seijdel, N., Sakmakidis, N., De Haan, E. H. F., Bohte, S. M., & Scholte, H. S. (2019). Implicit scene segmentation in deeper convolutional neural networks. In Proceedings of the 2019 Conference on Cognitive Computational Neuroscience (pp. 1059-1062). doi:10.32470/CCN.2019.1149-0.

Item is

Basic

show hide
Genre: Conference Paper

Files

show Files
hide Files
:
Seijdel_etal_2019_Implicit scene segmentation in deeper convolutional neural networks.pdf (Publisher version), 462KB
Name:
Seijdel_etal_2019_Implicit scene segmentation in deeper convolutional neural networks.pdf
Description:
-
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
2019
Copyright Info:
This work is licensed under the Creative Commons Attribution 3.0 Unported License. To view a copy of this license, visit http://creativecommons.org/licenses/by/3.0

Locators

show

Creators

show
hide
 Creators:
Seijdel, Noor1, Author              
Sakmakidis, N., Author
De Haan, E. H. F., Author
Bohte, S. M., Author
Scholte, H. S., Author
Affiliations:
1University of Amsterdam, Amsterdam, The Netherlands, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: Feedforward deep convolutional neural networks (DCNNs) are matching and even surpassing human performance on object recognition. This performance suggests that activation of a loose collection of image features could support the recognition of natural object categories, without dedicated systems to solve specific visual subtasks. Recent findings in humans however, suggest that while feedforward activity may suffice for sparse scenes with isolated objects, additional visual operations ('routines') that aid the recognition process (e.g. segmentation or grouping) are needed for more complex scenes. Linking human visual processing to performance of DCNNs with increasing depth, we here explored if, how, and when object information is differentiated from the backgrounds they appear on. To this end, we controlled the information in both objects and backgrounds, as well as the relationship between them by adding noise, manipulating background congruence and systematically occluding parts of the image. Results indicated less distinction between object- and background features for more shallow networks. For those networks, we observed a benefit of training on segmented objects (as compared to unsegmented objects). Overall, deeper networks trained on natural (unsegmented) scenes seem to perform implicit 'segmentation' of the objects from their background, possibly by improved selection of relevant features.

Details

show
hide
Language(s): eng - English
 Dates: 2019-09
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: Peer
 Identifiers: DOI: 10.32470/CCN.2019.1149-0
 Degree: -

Event

show
hide
Title: 2019 Conference on Cognitive Computational Neuroscience (CCN 2019)
Place of Event: Berlin, Germany
Start-/End Date: 2019-09-13 - 2019-09-16

Legal Case

show

Project information

show

Source 1

show
hide
Title: Proceedings of the 2019 Conference on Cognitive Computational Neuroscience
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 1059 - 1062 Identifier: -