Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 584

The DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.

Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes

Open access
Pohlen, Tobias, Hermans, Alexander, Mathias, Markus, Leibe, Bastian·2017·2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr.2017.353
Open this paper in CoChat — free account

Abstract

Semantic image segmentation is an essential component of modern autonomous driving systems, as an accurate understanding of the surrounding scene is crucial to navigation and action planning. Current state-of-the-art approaches in semantic image segmentation rely on pre-trained networks that were initially developed for classifying images as a whole. While these networks exhibit outstanding recognition performance (i.e., what is visible?), they lack localization accuracy (i.e., where precisely is something located?). Therefore, additional processing steps have to be performed in order to obtain pixel-accurate segmentation masks at the full image resolution. To alleviate this problem we propose a novel ResNet-like architecture that exhibits strong localization and recognition performance. We combine multi-scale context with pixel-level accuracy by using two processing streams within our network: One stream carries information at the full image resolution, enabling precise adherence to segment boundaries. The other stream undergoes a sequence of pooling operations to obtain robust features for recognition. The two streams are coupled at the full image resolution using residuals. Without additional processing steps and without pre-training, our approach achieves an intersection-over-union score of 71.8% on the Cityscapes dataset.

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.2017.353

Cites

20 of 20 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 20 references

Research works printed but not linked: 40

  1. 10.1109/CVPR.2015.7298959 · DOI · Paper page
  2. 10.1109/CVPR.2015.7298965 · DOI · Paper page
  3. 10.1109/CVPR.2014.19 · DOI · Paper page
  4. kundu, 2014, Joint semantic segmentation and 3d reconstruction from monocular video, ECCV, 703
  5. krizhevsky, 2012, ImageNet Classification with Deep Convolutional Networks, NIPS
  6. krähenbühl, 2011, Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials, NIPS
  7. 10.1109/ICCV.2015.162 · DOI · Paper page
  8. liu, 2015, Parsenet Looking wider to see better
  9. 10.1109/CVPR.2010.5539823 · DOI · Paper page
  10. 10.1007/s11263-008-0202-0 · DOI · Paper page
  11. badrinarayanan, 2015, Segnet A deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling
  12. al-rfou, 2016, Theano A Python framework for fast computation of mathematical expressions
  13. ghiasi, 2016, Laplacian Reconstruction and Refinement for Semantic Segmentation, ECCV
  14. gruslys, 2016, Memory-efficient backpropagation through time
  15. 10.1007/s11263-008-0140-x · DOI · Paper page
  16. hariharan, 2014, Simultaneous Detection and Segmentation, ECCV
  17. gu, 2009, Recognition using Regions, CVPR
  18. simonyan, 2015, Very Deep Convolutional Networks for Large-Scale Image Recognition, ICLRE
  19. 10.1109/CVPR.2015.7298594 · DOI · Paper page
  20. zhu, 2015, segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection, CVPR
  21. 10.1109/ICCV.2011.6126474 · DOI · Paper page
  22. 10.1109/CVPR.2015.7299146 · DOI
  23. xiao, 2009, Multiple view semantic segmentation for street view images, ICCV
  24. wu, 2016, Bridging category-level and instance-level semantic image segmentation
  25. chen, 2016, Training Deep Nets with Sublinear Memory Cost
  26. 10.1109/ICCV.2015.191 · DOI · Paper page
  27. 10.1109/CVPR.2015.7299025 · DOI · Paper page
  28. dieleman, 2015, Lasagne First Release
  29. 10.5244/C.23.84 · DOI
  30. 10.1109/CVPR.2012.6248007 · DOI
  31. gastal, 2011, Domain Transform for Edge-Aware Image and Video Processing, ACM Trans Graphics, 10.1145/2010324.1964964 · DOI · Paper page
  32. 10.1109/ICCVW.2009.5457720 · DOI
  33. 10.1007/978-3-319-46478-7_25 · DOI
  34. bergstra, 2013, Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures, ICML
  35. chen, 2016, VoxResNet Deep voxelwise residual networks for volumetric brain segmentation
  36. 10.1109/CVPR.2008.4587503 · DOI · Paper page
  37. schwing, 2015, Fully Connected Deep Structured Networks
  38. ošep, 2016, Multi-Scale Object Candidates for Generic Object Tracking in Street Scenes, ICRA
  39. 10.1109/ICCV.2015.178 · DOI · Paper page
  40. 10.1109/ICCV.2015.203 · DOI · Paper page

Cited by

Metadata

Authors
Pohlen, T., Hermans, A., Mathias, M., & Leibe, B.
Venue
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2017-07
Pages
3309-3318
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2017.353
OpenAlex
W2557406251
Cited by
584
References
20
FWCI
23.38
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.