Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 1,025

The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.

Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation

Open access
Liu, Chenxi, Chen, Liang-Chieh, Schroff, Florian, Adam, Hartwig, Hua, Wei, Yuille, Alan L., Fei-Fei, Li·2019·2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr.2019.00017
Open this paper in CoChat — free account

Abstract

Recently, Neural Architecture Search (NAS) has successfully identified neural network architectures that exceed human designed ones on large-scale image classification. In this paper, we study NAS for semantic image segmentation. Existing works often focus on searching the repeatable cell structure, while hand-designing the outer network structure that controls the spatial resolution changes. This choice simplifies the search space, but becomes increasingly problematic for dense image prediction which exhibits a lot more network level architectural variations. Therefore, we propose to search the network level structure in addition to the cell level structure, which forms a hierarchical architecture search space. We present a network level search space that includes many popular designs, and develop a formulation that allows efficient gradient-based architecture search (3 P100 GPU days on Cityscapes images). We demonstrate the effectiveness of the proposed method on the challenging Cityscapes, PASCAL VOC 2012, and ADE20K datasets. Auto-DeepLab, our architecture searched specifically for semantic image segmentation, attains state-of-the-art performance without any ImageNet pretraining.

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.2019.00017

Cites

31 of 31 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 31 references

Research works printed but not linked: 53

  1. sutskever, 2014, Sequence to sequence learning with neural networks, NIPS
  2. simonyan, 2015, Very deep convolutional networks for large-scale image recognition, ICLRE
  3. 10.1007/s11263-007-0109-1 · DOI · Paper page
  4. 10.1109/ICCV.2009.5459248 · DOI · Paper page
  5. 10.1109/CVPR.2015.7298594 · DOI · Paper page
  6. 10.1109/WACV.2018.00163 · DOI · Paper page
  7. 10.5244/C.31.10 · DOI
  8. 10.1109/CVPR.2017.518 · DOI · Paper page
  9. 10.1007/s11263-008-0202-0 · DOI · Paper page
  10. 10.1109/CVPR.2013.263 · DOI · Paper page
  11. jozefowicz, 2015, An empirical exploration of recurrent network architectures, ICML
  12. pohlen, 2017, Fullresolution residual networks for semantic segmentation in street scenes, CVPR
  13. qi, 2017, Deformable convolutional networks – coco detection and segmentation challenge 2017 entry, ICCV COCO Challenge Workshop
  14. real, 2017, Large-scale evolution of image classifiers, ICML
  15. 10.1007/978-3-642-97177-8_28 · DOI · Paper page
  16. 10.1109/CVPR.2018.00474 · DOI · Paper page
  17. saxena, 2016, Convolutional neural fabrics, NIPS
  18. sermanet, 2014, Overfeat: Integrated recognition, localization and detection using convolutional networks, ICLRE
  19. shin, 2018, Differentiable neural network architecture search, ICLR Workshop
  20. 10.1007/978-3-030-01228-1_22 · DOI
  21. 10.1109/ICIP.2013.6738831 · DOI · Paper page
  22. 10.1109/ICCV.2005.239 · DOI · Paper page
  23. he, 2014, Spatial pyramid pooling in deep convolutional networks for visual recognition, ECCV
  24. 10.1109/ICCV.2011.6126343 · DOI · Paper page
  25. he, 2004, Multiscale conditional random fields for image labeling, CVPR
  26. 10.1109/CVPR.2018.00907 · DOI · Paper page
  27. 10.1109/ICIP.2018.8451830 · DOI
  28. 10.1109/CVPR.2017.544 · DOI · Paper page
  29. pham, 2018, Efficient neural architecture search via parameter sharing, ICML
  30. 10.1109/CVPR.2015.7298636 · DOI · Paper page
  31. 10.1109/ICCV.2015.178 · DOI · Paper page
  32. 10.1109/CVPR.2015.7298959 · DOI · Paper page
  33. luo, 2018, Neural architecture optimization, NIPS
  34. 10.1109/CVPR.2016.396 · DOI · Paper page
  35. larsson, 2017, Fractalnet: Ultra-deep neural networks without residuals, ICLRE
  36. 10.1109/CVPR.2015.7299025 · DOI · Paper page
  37. fourure, 2017, Residual conv-deconv grid network for semantic segmentation, BMVC
  38. 10.1109/ICCV.2017.154 · DOI · Paper page
  39. ghiasi, 2018, Dropblock: A regularization method for convolutional networks, NIPS
  40. wu, 2018, Group normalization, ECCV
  41. 10.1109/CVPR.2018.00257 · DOI · Paper page
  42. 10.1109/CVPR.2018.00591 · DOI · Paper page
  43. baker, 2017, Designing neural network architectures using reinforcement learning, ICLRE
  44. chen, 2018, Searching for efficient multi-scale architectures for dense image prediction, NIPS
  45. cai, 2018, Efficient architecture search by network transformation, AAAI, 10.1609/aaai.v32i1.11709 · DOI · Paper page
  46. 10.1109/CVPR.2017.634 · DOI · Paper page
  47. zhang, 2018, Exfuse: Enhancing feature fusion for semantic segmentation, ECCV
  48. 10.1109/CVPR.2017.660 · DOI · Paper page
  49. lin, 2014, Microsoft coco: Common objects in context, ECCV
  50. liu, 2018, Hierarchical representations for efficient architecture search, ICLRE
  51. liu, 2018, Progressive neural architecture search, ECCV
  52. lin, 2017, Refinenet: Multipath refinement networks with identity mappings for highresolution semantic segmentation, CVPR
  53. lin, 2018, Multi-scale context intertwining for semantic segmentation, ECCV

Cited by

See all 1,025

Metadata

Authors
Liu, C., Chen, L.-C., Schroff, F., Adam, H., Hua, W., Yuille, A. L., & Fei-Fei, L.
Venue
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2019-06
Pages
82-92
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2019.00017
OpenAlex
W2963136578
Cited by
1,025
References
31
FWCI
59.29
Type
conference paper
Language
en
Open access
green
Licence

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation. https://app.cochat.ai/papers/10.1109/cvpr.2019.00017
The paper
Liu, C., Chen, L.-C., Schroff, F., Adam, H., Hua, W., Yuille, A. L., & Fei-Fei, L. (2019). Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr.2019.00017

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.