Deep Domain Adaptation by Geodesic Distance Minimization
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
In this paper, we propose a new approach called Deep LogCORAL for unsupervised visual domain adaptation. Our work builds on the recently proposed Deep CORAL method, which aims to train a convolutional neural network and simultaneously minimize the Euclidean distance of convariance matrices between the source and target domains. By observing that the second order statistical information (i.e. the covariance matrix) lies on a Riemannian manifold, we propose to use the Riemannian distance, approximated by Log-Euclidean distance, to replace the naive Euclidean distance in Deep CORAL. We also consider first-order information, and minimize the distance of mean vectors between two domains. We build an end-to-end model, in which we minimize both the classification loss, and the domain difference based on the first-order and second-order information between two domains. Our experiments on the benchmark Office dataset demonstrates the improvements of our newly proposed Deep LogCORAL approach over the Deep CORAL method, as well as the further improvement when optimizing both orders of information.
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.
Integrity signals
Registry
Cites
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.
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
Adversarial Discriminative Domain Adaptation
Tzeng, E., Hoffman, J., Saenko, K., & Darrell, T. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.316 · Cited by 5,154 · cited 2×
“Instead of optimizing the representation to minimize some measure of domain shift such as geodesic distance, DRCN[8] and ADDA [23] alternatively reconstruct the target domain from the source representation.”
BackgroundMethodDeep CORAL: Correlation Alignment for Deep Domain Adaptation
Sun, B., & Saenko, K. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-49409-8_35 · Cited by 3,757 · cited 3×
“Our work is mostly inspired by [20], which adds a new CORAL loss that calculates the Euclidean distance of two domain’s covariance matrices before the softmax layer.”
InfluentialAdapting visual category models to new domains
Saenko, K., Kulis, B., Fritz, M., & Darrell, T. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15561-1_16 · Cited by 2,847 · cited 2×
“This is known as the ”domain adaptation” problem [5] [9] [4] [6] [12] [13] [21] [18] [10] [7] [17].”
MethodTorralba, A., & Efros, A. A. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995347 · Cited by 2,440 · cited 2×
“Torrabla and Efros [22] pointed out that each existing visual recognition dataset more or loss has its own bias, which reveals the common existence of visual domain adaptation problems.”
BackgroundDeep domain confusion Maximizing for domain invariance
Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., & Darrell, T. (2014) · arXiv · doi:10.48550/arxiv.1412.3474 · Cited by 2,285
Return of Frustratingly Easy Domain Adaptation
Sun, B., Feng, J., & Saenko, K. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10306 · Cited by 2,004 · cited 2×
“Later unsupervised domain adaptation method [10][9][6][19][3] tried to improve the performance on the target domain by transferring knowledge from the target domain to the source domain without the need of target labels.”
Return of Frustratingly Easy Domain Adaptation
Sun, B., Feng, J., & Saenko, K. (2015) · arXiv · doi:10.48550/arxiv.1511.05547 · Cited by 2,004
Cited by
Domain Adaptive Faster R-CNN for Object Detection in the Wild
Chen, Y., Li, W., Sakaridis, C., Dai, D., & Van Gool, L. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00352 · Cited by 1,672
Self-citationA survey of unsupervised deep domain adaptation
Wilson, G., & Cook, D. J. (2020) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3400066 · Cited by 987
Dou, Q., Ouyang, C., Chen, C., Chen, H., & Heng, P.-A. (2018) · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/96 · Cited by 326
A Robust Learning Approach to Domain Adaptive Object Detection
Khodabandeh, M., Vahdat, A., Ranjbar, M., & Macready, W. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00057 · Cited by 274
Prototype Rectification for Few-Shot Learning
Liu, J., Song, L., & Qin, Y. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_43 · Cited by 269
Metadata
- Authors
- Wang, Y., Li, W., Dai, D., & Van Gool, L.
- Venue
- 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)
- Publisher
- IEEE
- Published
- 2017-10
- Pages
- 2651-2657
- ISSN
- 2473-9936 (ISSN-L)
- OpenAlex
- W2964013382
- Cited by
- 52
- References
- 7
- FWCI
- 2.29
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Deep Domain Adaptation by Geodesic Distance Minimization. https://app.cochat.ai/papers/10.1109/iccvw.2017.315
- The paper
- Wang, Y., Li, W., Dai, D., & Van Gool, L. (2017). Deep Domain Adaptation by Geodesic Distance Minimization. 2017 IEEE International Conference on Computer Vision Workshops (ICCVW). https://doi.org/10.1109/iccvw.2017.315
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.