A Neuro-Symbolic ASP Pipeline for Visual Question Answering

Eiter, ThomasInstitute of Logic and Computation, Vienna University of Technology (TU Wien), Austria (författare)

We present a neuro-symbolic visual question answering (VQA) pipeline for CLEVR, which is a well-known dataset that consists of pictures showing scenes with objects and questions related to them. Our pipeline covers (i) training neural networks for object classification and bounding-box prediction of the CLEVR scenes, (ii) statistical analysis on the distribution of prediction values of the neural networks to determine a threshold for high-confidence predictions, and (iii) a translation of CLEVR questions and network predictions that pass confidence thresholds into logic programmes so that we can compute the answers using an answer-set programming solver. By exploiting choice rules, we consider deterministic and non-deterministic scene encodings. Our experiments show that the non-deterministic scene encoding achieves good results 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. Furthermore, we show that restricting non-determinism to reasonable choices allows for more efficient implementations in comparison with related neuro-symbolic approaches without losing much accuracy.

Higuera, NelsonInstitute of Logic and Computation, Vienna University of Technology (TU Wien), Austria (författare)
Oetsch, JohannesInstitute of Logic and Computation, Vienna University of Technology (TU Wien), Austria(Swepub:hj)oetjoh (författare)
Pritz, MichaelInstitute of Logic and Computation, Vienna University of Technology (TU Wien), Austria (författare)
Institute of Logic and Computation, Vienna University of Technology (TU Wien), Austria (creator_code:org_t)

Ingår i:Theory and Practice of Logic Programming: Cambridge University Press22:5, s. 739-7541471-06841475-3081

Av författaren/redakt...: Eiter, Thomas; Higuera, Nelson; Oetsch, Johannes; Pritz, Michael

Om ämnet

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.