• Computer Science, Mathematics
  • Published in ICML 2019

Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering

@article{Vedantam2019ProbabilisticNM,
  title={Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering},
  author={Ramakrishna Vedantam and Karan Desai and Stefan Lee and Marcus Rohrbach and Dhruv Batra and Devi Parikh},
  journal={ArXiv},
  year={2019},
  volume={abs/1902.07864}
}
We propose a new class of probabilistic neural-symbolic models, that have symbolic functional programs as a latent, stochastic variable. Instantiated in the context of visual question answering, our probabilistic formulation offers two key conceptual advantages over prior neural-symbolic models for VQA. Firstly, the programs generated by our model are more understandable while requiring lesser number of teaching examples. Secondly, we show that one can pose counterfactual scenarios to the model… CONTINUE READING
4
Twitter Mentions

Figures, Tables, and Topics from this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 45 REFERENCES

Inferring and Executing Programs for Visual Reasoning

  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
VIEW 41 EXCERPTS
HIGHLY INFLUENTIAL

Fixing a Broken ELBO

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Learning to Reason: End-to-End Module Networks for Visual Question Answering

  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
VIEW 32 EXCERPTS
HIGHLY INFLUENTIAL

Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning

  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
VIEW 27 EXCERPTS
HIGHLY INFLUENTIAL

VQA: Visual Question Answering

Aishwarya Agrawal, Jiasen Lu, +4 authors Dhruv Batra
  • International Journal of Computer Vision
  • 2015
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL