CoChat
Sign Up
Cited by 152

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

Semantic segmentation of urban scenes by learning local class interactions

Volpi, Michele, Ferrari, Vittorio·2015·2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
DOI 10.1109/cvprw.2015.7301377
Open this paper in CoChat — free account

Abstract

Traditionally, land-cover mapping from remote sensing images is performed by classifying each atomic region in the image in isolation and by enforcing simple smoothing priors via random fields models as two independent steps. In this paper, we propose to model the segmentation problem by a discriminatively trained Conditional Random Field (CRF). To this end, we employ Structured Support Vector Machines (SSVM) to learn the weights of an informative set of appearance descriptors jointly with local class interactions. We propose a principled strategy to learn pairwise potentials encoding local class preferences from sparsely annotated ground truth. We show that this approach outperform standard baselines and more expressive CRF models, improving by 4-6 points the average class accuracy on a challenging dataset involving urban high resolution satellite imagery.

Overview

Integrity signals

Registry

Crossref · 10.1109/cvprw.2015.7301377

Cites

3 of 3 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?

  • Most densely labeled land cover datasets with sub-meter to meter-spatial resolutions have geographical coverage areas below 10 km2 and are located in concentrated regions.

    “But most of them have geographical coverage areas below 10 km2 and are located in concentrated regions, such as ISPRS Potsdam (ISPRS-Contest, 2018), ISPRS Vaihingen (ISPRS-Contest, 2018), Zurich Summer (Volpi and Ferrari, 2015), RIT-18 (Kemker et al., 2018), and Zeebruges (Marcos et al., 2018).”

    From Enabling country-scale land cover mapping with meter-resolution satellite imagery (2023) · cites this paper as Volpi and Ferrari, 2015

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 28

  1. 10.1109/TGRS.2007.907109 · DOI
  2. 10.1109/CVPR.2013.222 · DOI
  3. 10.1007/s11263-008-0140-x · DOI
  4. 10.1109/CVPR.2013.220 · DOI
  5. 10.1109/TGRS.2014.2326886 · DOI
  6. kluckner, 2009, Semantic classification in aerial imagery by integrating appearance and height information, ACCV 2009 Xidn (China), 1
  7. 10.1109/TPAMI.2007.1031 · DOI
  8. ladicky, 2010, Graph cut based inference with co-occurrence statistics, ECCV 2010 Hersonissos (Greece), 1
  9. lafferty, 2001, Conditional random fields: Probabilistic models for segmenting and labeling sequence data, ICML 2001 Williamstown (USA)
  10. 10.1109/ICCV.2011.6126219 · DOI
  11. 10.1109/JPROC.2012.2211551 · DOI
  12. nowozin, 2010, On parameter learning in CRF-based approaches to object class image segmentation, ECCV 2010 Hersonissos (Greece), 1
  13. 10.1109/TGRS.2005.852080 · DOI
  14. 10.1007/s11265-010-0483-8 · DOI
  15. 10.1016/S0166-218X(01)00336-5 · DOI
  16. congalton, 2008, Assessing the Accuracy of Remotely Sensed Data, 10.1201/9781420055139 · DOI
  17. 10.1023/A:1010933404324 · DOI · Paper page
  18. 10.1023/B:VISI.0000022288.19776.77 · DOI
  19. crammer, 2001, On the algorithmic implementation of multiclass kernel-based vector machines, Journal of Machine Learning Research, 2
  20. besag, 1974, Spatial interaction and the statistical analysis of lattice systems, Journal of the Royal Statistical Society Series B, 36, 192, 10.1111/j.2517-6161.1974.tb00999.x · DOI · Paper page
  21. 10.1109/CVPR.2008.4587799 · DOI
  22. 10.1126/science.1118051 · DOI
  23. nowozin, 2011, Structured learning and prediction in computer vision, Foundation and Trends in Computer Graphics and Vision, 6, 3
  24. 10.1109/TGRS.2012.2192741 · DOI
  25. 10.1109/ICCV.2007.4408986 · DOI
  26. 10.1007/s11263-012-0574-z · DOI
  27. tsochantaridis, 2005, Large margin methods for structured and interdependent output variables, Journal of Machine Learning Research, 6, 1453
  28. 10.1109/TGRS.2014.2321423 · DOI

Cited by

Sorted by citations

Metadata

Authors
Volpi, M., & Ferrari, V.
Venue
2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Publisher
IEEE
Published
2015-06
Pages
1-9
DOI
10.1109/cvprw.2015.7301377
Cited by
152
References
3

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