Women also Snowboard: Overcoming Bias in Captioning Models (Extended Abstract)

@inproceedings{Burns2018WomenAS,
  title={Women also Snowboard: Overcoming Bias in Captioning Models (Extended Abstract)},
  author={Kaylee Burns and Lisa Anne Hendricks and Trevor Darrell and Anna Rohrbach},
  booktitle={ECCV},
  year={2018}
}
Most machine learning methods are known to capture and exploit biases of the training data. While some biases are beneficial for learning, others are harmful. Specifically, image captioning models tend to exaggerate biases present in training data (e.g., if a word is present in 60% of training sentences, it might be predicted in 70% of sentences at test time). This can lead to incorrect captions in domains where unbiased captions are desired, or required, due to over-reliance on the learned… CONTINUE READING

Figures, Tables, and Topics from this paper.

Explore Further: Topics Discussed in This Paper

Citations

Publications citing this paper.
SHOWING 1-10 OF 58 CITATIONS

Highlighting Bias with Explainable Neural-Symbolic Visual Reasoning

VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Towards Explainable Neural-Symbolic Visual Reasoning

VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Algorithmic Fairness

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Epistemic Therapy for Bias in Automated Decision-Making

VIEW 5 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Mitigating Gender Bias in Natural Language Processing: Literature Review

VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Grounded Video Description

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Hide-and-Tell: Learning to Bridge Photo Streams for Visual Storytelling

VIEW 1 EXCERPT
CITES BACKGROUND

FILTER CITATIONS BY YEAR

2018
2020

CITATION STATISTICS

  • 6 Highly Influenced Citations

  • Averaged 24 Citations per year from 2018 through 2019

  • 333% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 48 REFERENCES

Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Rethinking the Inception Architecture for Computer Vision

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Show and tell: A neural image caption generator

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL