Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 1,377

The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.

Attention to Scale: Scale-Aware Semantic Image Segmentation

Open access
Chen, Liang-Chieh, Yang, Yi, Wang, Jiang, Xu, Wei, Yuille, Alan L.·2016·2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr.2016.396
Open this paper in CoChat — free account

Abstract

Incorporating multi-scale features in fully convolutional neural networks (FCNs) has been a key element to achieving state-of-the-art performance on semantic image segmentation. One common way to extract multi-scale features is to feed multiple resized input images to a shared deep network and then merge the resulting features for pixelwise classification. In this work, we propose an attention mechanism that learns to softly weight the multi-scale features at each pixel location. We adapt a state-of-the-art semantic image segmentation model, which we jointly train with multi-scale input images and the attention model. The proposed attention model not only outperforms averageand max-pooling, but allows us to diagnostically visualize the importance of features at different positions and scales. Moreover, we show that adding extra supervision to the output at each scale is essential to achieving excellent performance when merging multi-scale features. We demonstrate the effectiveness of our model with extensive experiments on three challenging datasets, including PASCAL-Person-Part, PASCAL VOC 2012 and a subset of MS-COCO 2014.

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.2016.396

Cites

15 of 15 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 15 references

Research works printed but not linked: 43

  1. mallat, 1999, A Wavelet Tour of Signal Processing
  2. 10.1109/CVPR.2015.7298965 · DOI · Paper page
  3. lee, 2015, Deeply-supervised nets, AISTATS
  4. krähenbühl, 2011, Efficient inference in fully connected crfs with gaussian edge potentials, NIPS
  5. 10.1109/ICCV.2015.162 · DOI · Paper page
  6. liu, 2015, Parsenet Looking wider to see better
  7. lin, 2014, Microsoft COCO: Common objects in context, ECCV
  8. he, 2014, Spatial pyramid pooling in deep convolutional networks for visual recognition, ECCV
  9. jia, 2014, Caffe Convolutional Architecture for Fast Feature Embedding
  10. 10.1109/TPAMI.2010.161 · DOI · Paper page
  11. 10.1109/CVPR.2014.471 · DOI · Paper page
  12. 10.1109/ITSC.2013.6728473 · DOI · Paper page
  13. 10.1007/BF00126140 · DOI
  14. 10.1109/CVPR.2014.81 · DOI · Paper page
  15. 10.1145/1964921.1964964 · DOI · Paper page
  16. 10.1109/ICCV.2011.6126343 · DOI · Paper page
  17. gregor, 2015, Draw: A recurrent neural network for image generation, ICML
  18. 10.1109/CVPR.2015.7298788 · DOI
  19. 10.1109/ICCV.2015.305 · DOI
  20. 10.1109/ICCV.2015.512 · DOI · Paper page
  21. 10.1109/ICCV.2015.164 · DOI · Paper page
  22. xiao, 2015, The application of two-level attention models in deep convolutional neural network for fine-grained image classification, CVPR
  23. 10.1109/ICCV.2015.184 · DOI
  24. chen, 2015, Semantic image segmentation with task-specific edge detection using cnns and a discriminatively trained domain transform
  25. mnih, 2014, Recurrent models of visual attention, NIPS
  26. chen, 2015, Learning deep structured models, ICML
  27. 10.1109/CVPR.2012.6248110 · DOI · Paper page
  28. 10.1109/ICCV.2015.191 · DOI · Paper page
  29. 10.1109/ICCV.2015.304 · DOI · Paper page
  30. evening, 2005, Adobe Photoshop CS2 for Photographers A professional image editor's guide to the creative use of Photoshop for the Macintosh and PC, 10.4324/9780080481906 · doi:10.4324/9780080481906
  31. ba, 2014, Multiple object recognition with visual attention
  32. bahdanau, 2015, Neural machine translation by jointly learning to align and translate, ICLRE
  33. 10.1109/ICCV.2015.338 · DOI · Paper page
  34. 10.1109/ICCV.2015.286 · DOI · Paper page
  35. simonyan, 2015, Very deep convolutional networks for large-scale image recognition, ICLRE
  36. chen, 2015, ABC-CNN An attention based convolutional neural network for visual question answering
  37. pinheiro, 2013, Recurrent Convolutional Neural Networks for Scene Parsing
  38. sharma, 2015, Action recognition using visual attention
  39. sermanet, 2014, Overfeat: Integrated recognition, localization and detection using convolutional networks, ICLRE
  40. 10.1109/ICCV.2015.178 · DOI · Paper page
  41. 10.1109/CVPR.2015.7298959 · DOI · Paper page
  42. papandreou, 2015, Untangling local and global deformations in deep convolutional networks for image classification and sliding window detection, CVPR
  43. papandreou, 2015, Weakly- and semi-supervised learning of a dcnn for semantic image segmentation, ICCV

Cited by

Metadata

Authors
Chen, L.-C., Yang, Y., Wang, J., Xu, W., & Yuille, A. L.
Venue
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2016-06
Pages
3640-3649
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2016.396
OpenAlex
W2962891704
Cited by
1,377
References
15
FWCI
54.15
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.