Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering

@article{Agrawal2017DontJA,
  title={Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering},
  author={Aishwarya Agrawal and Rishabh Jain and Mark Johnson and Aniruddha Kembhavi},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2017},
  pages={4971-4980}
}
A number of studies have found that today's Visual Question Answering (VQA) models are heavily driven by superficial correlations in the training data and lack sufficient image grounding. To encourage development of models geared towards the latter, we propose a new setting for VQA where for every question type, train and test sets have different prior distributions of answers. Specifically, we present new splits of the VQA v1 and VQA v2 datasets, which we call Visual Question Answering under… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 63 CITATIONS

Question Splitting and Unbalanced Multi-modal Pooling for VQA

  • 2019 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)
  • 2019
VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Actively Seeking and Learning from Live Data

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Self-Critical Reasoning for Robust Visual Question Answering

VIEW 10 EXCERPTS
CITES RESULTS, METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2016
2019

CITATION STATISTICS

  • 22 Highly Influenced Citations

  • Averaged 20 Citations per year from 2017 through 2019

  • 57% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 41 REFERENCES

Stacked Attention Networks for Image Question Answering

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Yin and Yang: Balancing and Answering Binary Visual Questions

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 4 EXCERPTS

Cross-Dataset Adaptation for Visual Question Answering

  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
VIEW 1 EXCERPT

An Empirical Evaluation of Visual Question Answering for Novel Objects

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
VIEW 1 EXCERPT

An analysis of visual question answering algorithms

K. Kafle, K. Christopher
  • ICCV,
  • 2017
VIEW 1 EXCERPT