Colorization as a Proxy Task for Visual Understanding

@article{Larsson2017ColorizationAA,
  title={Colorization as a Proxy Task for Visual Understanding},
  author={Gustav Larsson and Michael Maire and Gregory Shakhnarovich},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={840-849}
}
We investigate and improve self-supervision as a drop-in replacement for ImageNet pretraining, focusing on automatic colorization as the proxy task. Self-supervised training has been shown to be more promising for utilizing unlabeled data than other, traditional unsupervised learning methods. We build on this success and evaluate the ability of our self-supervised network in several contexts. On VOC segmentation and classification tasks, we present results that are state-of-the-art among… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 81 CITATIONS

Image Synthesis for Self-Supervised Visual Representation Learning

VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Pattern Recognition

  • Lecture Notes in Computer Science
  • 2018
VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Surrogate Supervision for Medical Image Analysis: Effective Deep Learning From Limited Quantities of Labeled Data

  • 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)
  • 2019
VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

UNSUPERVISED DOMAIN ADAPTATION

Yu Sun, Eric Tzeng, Trevor Darrell, Alexei A. Efros
  • 2019
VIEW 4 EXCERPTS
HIGHLY INFLUENCED

Unsupervised Domain Adaptation through Self-Supervision

Yu Sun, Eric Tzeng, Trevor Darrell, Alexei A. Efros
  • ArXiv
  • 2019
VIEW 4 EXCERPTS
HIGHLY INFLUENCED

Learning Image Representations by Completing Damaged Jigsaw Puzzles

  • 2018 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • 2018
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Regularizing Deep Networks by Modeling and Predicting Label Structure

  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
VIEW 4 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS

FILTER CITATIONS BY YEAR

2016
2019

CITATION STATISTICS

  • 14 Highly Influenced Citations

  • Averaged 27 Citations per year from 2017 through 2019

  • 17% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 46 REFERENCES

Fully convolutional networks for semantic segmentation

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Context Encoders: Feature Learning by Inpainting

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016

Learning Features by Watching Objects Move

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 1 EXCERPT