Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 1,464

The DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.

Context Encoding for Semantic Segmentation

Open access
Zhang, Hang, Dana, Kristin, Shi, Jianping, Zhang, Zhongyue, Wang, Xiaogang, Tyagi, Ambrish, Agrawal, Amit·2018·2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
DOI 10.1109/cvpr.2018.00747
Open this paper in CoChat — free account

Abstract

Recent work has made significant progress in improving spatial resolution for pixelwise labeling with Fully Convolutional Network (FCN) framework by employing Dilated/Atrous convolution, utilizing multi-scale features and refining boundaries. In this paper, we explore the impact of global contextual information in semantic segmentation by introducing the Context Encoding Module, which captures the semantic context of scenes and selectively highlights class-dependent featuremaps. The proposed Context Encoding Module significantly improves semantic segmentation results with only marginal extra computation cost over FCN. Our approach has achieved new state-of-the-art results 51.7% mIoU on PASCAL-Context, 85.9% mIoU on PASCAL VOC 2012. Our single model achieves a final score of 0.5567 on ADE20K test set, which surpasses the winning entry of COCO-Place Challenge 2017. In addition, we also explore how the Context Encoding Module can improve the feature representation of relatively shallow networks for the image classification on CIFAR-10 dataset. Our 14 layer network has achieved an error rate of 3.45%, which is comparable with state-of-the-art approaches with over 10Ã- more layers. The source code for the complete system are publicly available1.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr.2018.00747

Cites

24 of 24 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 24 references

Research works printed but not linked: 37

  1. 10.1109/ICCV.2017.296 · DOI
  2. lin, 2014, Microsoft coco: Common objects in context, European Conference on Computer Vision, 740
  3. 10.1109/CVPR.2015.7298965 · DOI · Paper page
  4. 10.1109/ICCV.2015.162 · DOI · Paper page
  5. liu, 2015, Parsenet Looking wider to see better
  6. krizhevsky, 2009, Learning multiple layers of features from tiny images
  7. kang, 2016, Shakeout: A new regularized deep neural network training scheme, AAAI, 1751
  8. 10.1007/978-3-319-46475-6_33 · DOI · Paper page
  9. 10.1109/CVPR.2016.572 · DOI · Paper page
  10. huang, 2017, Arbitrary style transfer in realtime with adaptive instance normalization, ICCV
  11. jaderberg, 2015, Spatial transformer networks, Advances in neural information processing systems, 2017
  12. 10.1007/BFb0026683 · DOI · Paper page
  13. 10.1109/CVPR.2010.5540039 · DOI · Paper page
  14. wu, 2016, Wider or deeper Revisiting the resnet model for visual recognition
  15. xie, 2016, Aggregated residual transformations for deep neural networks
  16. 10.1109/CVPR.2017.544 · DOI · Paper page
  17. 10.1109/CVPR.2017.660 · DOI · Paper page
  18. 10.1109/CVPR.2017.309 · DOI · Paper page
  19. zhang, 0, Multi-style generative network for real-time transfer
  20. 10.1109/CVPR.2017.75 · DOI · Paper page
  21. dumoulin, 2016, A learned representation for artistic style
  22. 10.1109/ICCV.2015.178 · DOI · Paper page
  23. 10.1109/CVPR.2005.16 · DOI · Paper page
  24. 10.1109/CVPR.2014.81 · DOI · Paper page
  25. 10.1007/978-3-319-10584-0_20 · DOI · Paper page
  26. chen, 2017, Rethinking atrous convolution for semantic image segmentation
  27. csurka, 2004, Visual categorization with bags of keypoints, Workshop on Statistical Learning in Computer Vision ECCV, 1, 1
  28. 10.1109/CVPR.2015.7299007 · DOI · Paper page
  29. wu, 2016, Bridging category-level and instance-level semantic image segmentation
  30. 10.1109/ICCV.2015.191 · DOI · Paper page
  31. varma, 2002, Classifying images of materials: Achieving viewpoint and illumination independence, European Conference on Computer Vision, 255
  32. srivastava, 2014, Dropout: a simple way to prevent neural networks from overfitting, Journal of Machine Learning Research, 15, 1929
  33. 10.1109/CVPR.2017.556 · DOI
  34. perronnin, 2010, Improving the fisher kernel for large-scale image classification, European Conference on Computer Vision, 143
  35. paszke, 2017, On Automatic Differentiation
  36. sivic, 2005, Discovering objects and their location in images, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1, 1, 370, 10.1109/ICCV.2005.77 · DOI · Paper page
  37. schwartz, 2016, Material recognition from local appearance in global context

Cited by

Metadata

Authors
Zhang, H., Dana, K., Shi, J., Zhang, Z., Wang, X., Tyagi, A., & Agrawal, A.
Venue
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Publisher
IEEE
Published
2018-06
Pages
7151-7160
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2018.00747
OpenAlex
W2963727650
Cited by
1,464
References
24
FWCI
53.46
Type
conference paper
Language
en
Open access
green

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

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.