<div class="csl-bib-body">
<div class="csl-entry">Eiter, T., Oetsch, J., Pritz, M., & Higuera Ruiz, N. N. (2022, February 28). <i>A Confidence-Based Interface for Neuro-Symbolic Visual Question Answering</i> [Poster Presentation]. First International Workshop on Combining Learning and Reasoning: Programming Languages, Formalisms, and Representations (CLeaR 2022), Vancouver, Canada. http://hdl.handle.net/20.500.12708/146112</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/146112
-
dc.description.abstract
We present a neuro-symbolic visual question answering
(VQA) approach for the CLEVR dataset that is based on the
combination of deep neural networks and answer-set program-
ming (ASP), a logic-based paradigm for declarative problem
solving. We provide a translation mechanism for the questions
included in CLEVR to ASP programs. By exploiting choice
rules, we consider deterministic and non-deterministic scene
encodings. In addition, we introduce a confidence-based inter-
face between the ASP module and the neural network which
allows us to restrict the non-determinism to objects classified
by the network with high confidence. Our experiments show
that the non-deterministic scene encoding achieves good re-
sults even if the neural networks are trained rather poorly in
comparison with the deterministic approach. This is important
for building robust VQA systems if network predictions are
less-than perfect.
en
dc.description.sponsorship
Robert Bosch GmbH
-
dc.language.iso
en
-
dc.subject
neuro-symbolic reasoning
en
dc.subject
visual-question answering
en
dc.subject
answer-set programming
en
dc.subject
deep learning
en
dc.title
A Confidence-Based Interface for Neuro-Symbolic Visual Question Answering
en
dc.type
Presentation
en
dc.type
Vortrag
de
dc.contributor.affiliation
TU Wien, Austria
-
dc.relation.grantno
114402 - TU Wien - Bosch
-
dc.type.category
Poster Presentation
-
tuw.project.title
Advanced context-based reasoning over heterogeneous data sources
-
tuw.researchTopic.id
I1
-
tuw.researchTopic.name
Logic and Computation
-
tuw.researchTopic.value
100
-
tuw.publication.orgunit
E192-03 - Forschungsbereich Knowledge Based Systems
-
tuw.author.orcid
0000-0001-6003-6345
-
tuw.event.name
First International Workshop on Combining Learning and Reasoning: Programming Languages, Formalisms, and Representations (CLeaR 2022)
en
tuw.event.startdate
28-02-2022
-
tuw.event.enddate
28-02-2022
-
tuw.event.online
Hybrid
-
tuw.event.type
Event for scientific audience
-
tuw.event.place
Vancouver
-
tuw.event.country
CA
-
tuw.event.presenter
Oetsch, Johannes
-
tuw.presentation.online
Online
-
wb.sciencebranch
Informatik
-
wb.sciencebranch.oefos
1020
-
wb.sciencebranch.value
100
-
item.grantfulltext
restricted
-
item.openairecristype
http://purl.org/coar/resource_type/c_18co
-
item.openairetype
conference poster not in proceedings
-
item.cerifentitytype
Publications
-
item.fulltext
no Fulltext
-
item.languageiso639-1
en
-
crisitem.author.dept
E192 - Institut für Logic and Computation
-
crisitem.author.dept
E192-03 - Forschungsbereich Knowledge Based Systems
-
crisitem.author.dept
TU Wien, Austria
-
crisitem.author.dept
E192-03 - Forschungsbereich Knowledge Based Systems
