CoChat
Sign Up
Cited by 43

The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.

Learning Confidence Measures by Multi-modal Convolutional Neural Networks

Fu, Zehua, Ardabilian Fard, Mohsen·2018·2018 IEEE Winter Conference on Applications of Computer Vision (WACV)
DOI 10.1109/wacv.2018.00149
Open this paper in CoChat — free account

Abstract

In stereo matching, the correctness of stereo pairs matches, also called confidence, is used to improve the dense disparity estimation result. In this paper, we propose a multi-modal deep learning approach for stereo matching confidence estimation. The input of our method is composed of two modalities, the initial disparity maps, and its reference color image. To effectively combine these two modalities, we explore and study multiple convolutional neural network (CNN) structures for our specific confidence prediction tasks. To the best of our knowledge, this is the first approach reported in the literature combining multiple modalities and patch based deep learning to predict the confidence. The experiments on KITTI datasets demonstrate that our multi-modal confidence network can significantly outperform the state-of-the-art methods.

Overview

Integrity signals

Registry

Crossref · 10.1109/wacv.2018.00149

Cites

4 of 4 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Research works printed but not linked: 27

  1. zhong, 2016, Detecting ground control points via convolutional neural network for stereo matching, Multimedia Tools and Applications, 1
  2. glorot, 2010, Understanding the difficulty of training deep feedforward neural networks, Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS10) Society for Artificial Intelligence and Statistics
  3. 10.1109/CVPR.2013.46 · DOI
  4. hu, 2012, A quantitative evaluation of confidence measures for stereo vision, IEEE Transactions on Pattern Analysis and Machine Intelligence, 34, 2121, 10.1109/TPAMI.2012.46 · DOI
  5. 10.1109/CVPR.2014.223 · DOI · Paper page
  6. 10.1109/CVPR.2014.223 · DOI · Paper page
  7. 10.1109/CVPR.2015.7298925 · DOI · Paper page
  8. park, 0, Leveraging stereo matching with learning-based confidence measures, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 101
  9. 10.1109/3DV.2016.61 · DOI
  10. yu, 0, Multi-scale context aggregation by di-lated convolutions, International Conference on Learning Representations (ICLR)
  11. collobert, 0, Torch7: A Matlab-like Environment for Machine Learning, BigLearn NIPS Workshop
  12. 10.1007/s11263-015-0877-y · DOI
  13. chetlur, 2014, cudnn: Efficient primitives for deep learning, CoRR, abs 1410 759
  14. dumoulin, 2016, A guide to convolution arithmetic for deep learning, CoRR, abs 1603 7285
  15. zbontar, 2016, Stereo matching by training a convolutional neural network to compare image patches, Journal of Machine Learning Research, 17, 1
  16. dong, 2014, Learning a Deep Convolutional Network for Image Super-Resolution, 184
  17. 10.1177/0278364913491297 · DOI · Paper page
  18. 10.1109/TPAMI.2002.1023808 · DOI
  19. 10.1109/CVPR.2012.6248074 · DOI · Paper page
  20. 10.1177/02783640122067525 · DOI
  21. 10.5244/C.30.46 · DOI
  22. 10.1109/CVPRW.2017.54 · DOI
  23. 10.1109/CVPR.2017.483 · DOI
  24. 10.1023/A:1014573219977 · DOI · Paper page
  25. 10.1109/ICCV.2017.559 · DOI
  26. 10.1109/CVPR.2014.210 · DOI
  27. 10.5244/C.30.23 · DOI

Cited by

Sorted by citations

See all 43

Metadata

Authors
Fu, Z., & Ardabilian Fard, M.
Venue
2018 IEEE Winter Conference on Applications of Computer Vision (WACV)
Publisher
IEEE
Published
2018-03
Pages
1321-1330
DOI
10.1109/wacv.2018.00149
Cited by
43
References
4

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review