CoChat
Sign Up
Cited by 5,154Domain Adaptation and Few-Shot LearningGenerative Adversarial Networks and Image SynthesisAdvanced Neural Network Applications

Adversarial Discriminative Domain Adaptation

Tzeng, Eric, Hoffman, Judy, Saenko, Kate, Darrell, Trevor·2017·2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr.2017.316
Open this paper in CoChat — free account

Abstract

Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains. They can also improve recognition despite the presence of domain shift or dataset bias: recent adversarial approaches to unsupervised domain adaptation reduce the difference between the training and test domain distributions and thus improve generalization performance. However, while generative adversarial networks (GANs) show compelling visualizations, they are not optimal on discriminative tasks and can be limited to smaller shifts. On the other hand, discriminative approaches can handle larger domain shifts, but impose tied weights on the model and do not exploit a GAN-based loss. In this work, we first outline a novel generalized framework for adversarial adaptation, which subsumes recent state-of-the-art approaches as special cases, and use this generalized view to better relate prior approaches. We then propose a previously unexplored instance of our general framework which combines discriminative modeling, untied weight sharing, and a GAN loss, which we call Adversarial Discriminative Domain Adaptation (ADDA). We show that ADDA is more effective yet considerably simpler than competing domain-adversarial methods, and demonstrate the promise of our approach by exceeding state-of-the-art unsupervised adaptation results on standard domain adaptation tasks as well as a difficult cross-modality object classification task.

Integrity signals

Registry

Crossref · 10.1109/cvpr.2017.316

Cites

31 of 31 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, 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?

  • Standard domain adaptation benchmarks include training on MNIST but testing on SVHN street signs, as well as transfers across datasets containing different renditions in DomainNet and Office-Home.

    “For example, standard domain adaptation benchmarks include training on MNIST but testing on SVHN street signs (LeCun et al., 1998; Yuval et al., 2011; Tzeng et al., 2017; Hoffman et al., 2018), as well as transfers across datasets containing different renditions (e.g., photos, clipart, sketches) in DomainNet (Peng et al., 2019) and the Office-Home dataset (Venkateswara et al., 2017).”

    From WILDS: A Benchmark of in-the-Wild Distribution Shifts (2020) · cites this paper as Tzeng et al., 2017

Cites

Flagged first, then by citations

3 of the 34 references couldn’t be matched to a known paper.

Cited by

Sorted by citations

Related

Authors
Tzeng, E., Hoffman, J., Saenko, K., & Darrell, T.
Affiliations
  • University of California, Berkeley (US)
  • Stanford University (US)
  • Boston University (US)
ORCID
Venue
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2017-07
Pages
2962-2971
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2017.316
OpenAlex
W2593768305
Cited by
5,154
References
34
Citations by year
2026: 259 · 2025: 482 · 2024: 611 · 2023: 749 · 2022: 696 · 2021: 854 · 2020: 753 · 2019: 553 · 2018: 179 · 2017: 17 · 2013: 1
FWCI
187.34
Type
conference paper
Language
en
Open access
closed
Locations
IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
Funders
  • National Science Foundation
  • Defense Advanced Research Projects Agency
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
Keywords
unsupervised domain adaptation, adversarial learning, generative adversarial networks, domain shift, domain adversarial neural networks

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