VisDA: A Synthetic-to-Real Benchmark for Visual Domain Adaptation
Abstract
The success of machine learning methods on visual recognition tasks is highly dependent on access to large labeled datasets. However, real training images are expensive to collect and annotate for both computer vision and robotic applications. The synthetic images are easy to generate but model performance often drops significantly on data from a new deployment domain, a problem known as dataset shift, or dataset bias. Changes in the visual domain can include lighting, camera pose and background variation, as well as general changes in how the image data is collected. While this problem has been studied extensively in the domain adaptation literature, progress has been limited by the lack of large-scale challenge benchmarks.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Spaceborne images have fundamentally different visual properties from computer-generated synthetic images, so CNN performance on synthetic images does not translate to an equal level of performance on spaceborne images encountered during a mission.
“However, spaceborne images have fundamentally different visual properties compared to computer-generated synthetic images, so CNN performance on synthetic images does not translate to the equal level of performance on spaceborne images encountered during a mission.”
From Robust multi-task learning and online refinement for spacecraft pose estimation across domain gap (2024) · cites this paper as Peng et al., 2018
The citation lists haven’t been fetched yet
References 25 · Cited by 196
- Authors
- Peng, X., Usman, B., Kaushik, N., Wang, D., Hoffman, J., & Saenko, K.
- Affiliations
- Boston University (US)
- University of California, Berkeley (US)
- Venue
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
- Publisher
- IEEE
- Published
- 2018-06
- Pages
- 2102-21025
- OpenAlex
- W2885018852
- Cited by
- 196
- References
- 25
- Citations by year
- 2026: 12 · 2025: 28 · 2024: 34 · 2023: 34 · 2022: 20 · 2021: 37 · 2020: 24 · 2019: 6 · 2018: 1
- FWCI
- 6.91
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Keywords
- visual domain adaptation, synthetic-to-real transfer, distribution shift, benchmark, synthetic images, illumination variation, background variation, visual recognition, robot vision
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
