CoChat

DeceptionNet: Network-Driven Domain Randomization

Open access
Zakharov, Sergey, Kehl, Wadim, Ilic, Slobodan · 2019 · 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Cited by 78

The DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.

Abstract

We present a novel approach to tackle domain adaptation between synthetic and real data. Instead, of employing "blind" domain randomization, i.e., augmenting synthetic renderings with random backgrounds or changing illumination and colorization, we leverage the task network as its own adversarial guide toward useful augmentations that maximize the uncertainty of the output. To this end, we design a min-max optimization scheme where a given task competes against a special deception network to minimize the task error subject to the specific constraints enforced by the deceiver. The deception network samples from a family of differentiable pixel-level perturbations and exploits the task architecture to find the most destructive augmentations. Unlike GAN-based approaches that require unlabeled data from the target domain, our method achieves robust mappings that scale well to multiple target distributions from source data alone. We apply our framework to the tasks of digit recognition on enhanced MNIST variants, classification and object pose estimation on the Cropped LineMOD dataset as well as semantic segmentation on the Cityscapes dataset and compare it to a number of domain adaptation approaches, thereby demonstrating similar results with superior generalization capabilities.

Overview

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

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Integrity signals

Registry

Crossref · 10.1109/iccv.2019.00062

Cites

23 of 23 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.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Research works printed but not linked: 36

  1. sadeghi, 2016, Cad2rl: Real single-image flight without a single real image, arXiv preprint arXiv 1611 04201
  2. 10.1145/360825.360839 · DOI · Paper page
  3. 10.1109/ICCV.2017.609 · DOI · Paper page
  4. ratner, 2017, Learning to compose domain-specific transformations for data augmentation, Advances in neural information processing systems
  5. 10.1109/CVPR.2018.00490 · DOI
  6. 10.1109/IROS40897.2019.8967829 · DOI
  7. mahler, 2017, Learning deep policies for robot bin picking by simulating robust grasping sequences, CoRL
  8. 10.1007/978-3-030-01264-9_49 · DOI
  9. 10.1109/TPAMI.2010.161 · DOI · Paper page
  10. antoniou, 2017, Data augmentation generative adversarial networks, arXiv preprint arXiv 1711 04340
  11. ledig, 2016, Photo-realistic single image super-resolution using a generative adversarial network, CoRR
  12. lee, 2019, Spigan: Privileged adversarial learning from simulation, ICLRE
  13. liu, 2016, Coupled generative adversarial networks, CoRR
  14. lin, 2014, Microsoft coco: common objects in context, ECCV
  15. 10.1109/CVPR.2015.7298930 · DOI · Paper page
  16. 10.1109/ICCV.2017.244 · DOI · Paper page
  17. 10.1109/ICCV.2017.223 · DOI · Paper page
  18. 10.1109/ICCV.2019.00203 · DOI · Paper page
  19. 10.1109/3DV.2018.00012 · DOI
  20. 10.1109/CVPR.2016.350 · DOI · Paper page
  21. devries, 2017, Dataset augmentation in feature space, arXiv preprint arXiv 1702 05464
  22. 10.1109/CVPR.2018.00395 · DOI · Paper page
  23. ganin, 2015, Unsupervised domain adaptation by backpropagation, ICML
  24. 10.1109/WACV.2017.103 · DOI · Paper page
  25. hoffman, 2016, Fcns in the wild: Pixel-level adversarial and constraint-based adaptation, arXiv preprint arXiv 1612 02649
  26. 10.1007/s10851-009-0161-2 · DOI · Paper page
  27. babenko, 2014, Neural codes for image retrieval, CoRR
  28. bousmalis, 2016, Domain separation networks, NIPS
  29. 10.1109/CVPR.2018.00823 · DOI · Paper page
  30. 10.1109/CVPR.2019.00194 · DOI · Paper page
  31. 10.1109/ICCV.2017.220 · DOI · Paper page
  32. taigman, 2017, Unsupervised cross-domain image generation, ICLRE
  33. 10.1109/CVPR.2018.00780 · DOI · Paper page
  34. 10.1109/ICDAR.2003.1227801 · DOI · Paper page
  35. 10.1109/CVPR.2017.241 · DOI · Paper page
  36. 10.3389/frobt.2018.00066 · DOI · Paper page

Cited by

See all 78

Metadata

Authors
Zakharov, S., Kehl, W., & Ilic, S.
Venue
2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2019-10
Pages
532-541
OpenAlex
W2926800893
Cited by
78
References
23
FWCI
4.91
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.