Eiter, T., Oetsch, J., Pritz, M., & Higuera Ruiz, N. N. (2022, February 28). A Confidence-Based Interface for Neuro-Symbolic Visual Question Answering [Poster Presentation]. First International Workshop on Combining Learning and Reasoning: Programming Languages, Formalisms, and Representations (CLeaR 2022), Vancouver, Canada.
E192-03 - Forschungsbereich Knowledge Based Systems
-
Date (published):
28-Feb-2022
-
Event name:
First International Workshop on Combining Learning and Reasoning: Programming Languages, Formalisms, and Representations (CLeaR 2022)
en
Event date:
28-Feb-2022
-
Event place:
Vancouver, Canada
-
Keywords:
neuro-symbolic reasoning; visual-question answering; answer-set programming; deep learning
en
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
Project title:
Advanced context-based reasoning over heterogeneous data sources: 114402 - TU Wien - Bosch (Robert Bosch GmbH)