Deep Visual Domain Adaptation
Open accessThe DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index.
Abstract
Domain adaptation (DA) aims at improving the performance of a model on target domains by transferring the knowledge contained in different but related source domains. With recent advances in deep learning models which are extremely data hungry, the interest for visual DA has significantly increased in the last decade and the number of related work in the field exploded. The aim of this paper, therefore, is to give a comprehensive overview of deep domain adaptation methods for computer vision applications. First, we detail and compared different possible ways of exploiting deep architectures for domain adaptation. Then, we propose an overview of recent trends in deep visual DA. Finally, we mention a few improvement strategies, orthogonal to these methods, that can be applied to these models. While we mainly focus on image classification, we give pointers to papers that extend these ideas for other applications such as semantic segmentation, object detection, person re-identifications, and others.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 1×
“To minimise the impact of noisy pseudo-labels during alignment, curriculum learning-based [108] approaches have been explored.”
BackgroundAdversarial 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
Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization
Huang, X., & Belongie, S. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.167 · Cited by 5,076
Learning Transferable Features with Deep Adaptation Networks
Long, M., Cao, Y., Wang, J., & Jordan, M. I. (2015) · arXiv · doi:10.48550/arxiv.1502.02791 · Cited by 4,505 · cited 3×
“To minimize the distribution discrepancy, most often the Kernelized MMD loss is used [26], [32], but amongst the alternative losses proposed, we can mention the Central Moment Discrepancy [33], CORAL loss [27], or Wasserstein distance [34], [35].”
MethodDeep 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 2×
“To minimize the distribution discrepancy, most often the Kernelized MMD loss is used [26], [32], but amongst the alternative losses proposed, we can mention the Central Moment Discrepancy [33], CORAL loss [27], or Wasserstein distance [34], [35].”
MethodAdapting 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 1×
“Right: we show Amazon (A) and Webcam (W) data from the Office 31 [14] benchmark set clustered together with SURF-BOV and AlexNet features.”
MethodCyCADA: Cycle-Consistent Adversarial Domain Adaptation
Hoffman, J., Tzeng, E., Park, T., Zhu, J.-Y., Isola, P., Saenko, K., Efros, A. A., & Darrell, T. (2017) · arXiv · doi:10.48550/arxiv.1711.03213 · Cited by 2,656 · cited 2×
“CyCADA [87], combines pixel-level and feature-level adaptation where both structural and semantic consistency is enforced.”
BackgroundDeep visual domain adaptation: A survey
Wang, M., & Deng, W. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.05.083 · Cited by 2,209
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 3×
“As shown in [1], [10], [21], [22], to cite a few examples, using such DA methods with deep features yields further performance improvement on the target data.”
BackgroundMethodIntegrating structured biological data by Kernel Maximum Mean Discrepancy
Borgwardt, K. M., Gretton, A., Rasch, M. J., Kriegel, H.-P., Schölkopf, B., & Smola, A. J. (2006) · Bioinformatics · doi:10.1093/bioinformatics/btl242 · Cited by 1,674
Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., & Krishnan, D. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.18 · Cited by 1,603
ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
Vu, T.-H., Jain, H., Bucher, M., Cord, M., & Perez, P. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00262 · Cited by 1,524 · cited 1×
“Similarly, [122] proposes an adversarial loss for entropy minimization used to bridge the domain gap between synthetic to real semantic segmentation adaptation.”
MethodUnsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-training
Zou, Y., Yu, Z., Vijaya Kumar, B. V. K., & Wang, J. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01219-9_18 · Cited by 1,464 · cited 1×
“Curriculum-learning based DA methods with progressively including harder and harder pseudo-labeled target data was also used for cross-domain person re-identification [113]– [115] and image segmentation [116]–[118].”
MethodBousmalis, K., Trigeorgis, G., Silberman, N., Krishnan, D., & Erhan, D. (2016) · arXiv · doi:10.48550/arxiv.1608.06019 · Cited by 1,208 · cited 1×
“[76] integrates both domain-specific encoders and shared encoders, and the model integrates a reconstruction loss for a shared decoder that rely on both domain specific and shared representations.”
BackgroundStrong-Weak Distribution Alignment for Adaptive Object Detection
Saito, K., Ushiku, Y., Harada, T., & Saenko, K. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00712 · Cited by 819
Bidirectional Learning for Domain Adaptation of Semantic Segmentation
Li, Y., Yuan, L., & Vasconcelos, N. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00710 · Cited by 704 · cited 1×
“[106] used predicted labels with high confidence in a bidirectional learning framework for semantic segmentation, where the image translation model and the segmentation adaptation model are learned alternatively.”
MethodAdaptive batch normalization for practical domain adaptation
Li, Y., Wang, N., Shi, J., Hou, X., & Liu, J. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2018.03.005 · Cited by 601
Progressive Feature Alignment for Unsupervised Domain Adaptation
Chen, C., Xie, W., Huang, W., Rong, Y., Ding, X., Huang, Y., Xu, T., & Huang, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00072 · Cited by 481 · cited 1×
“Pseudolabeling confidence scores are typically determined using the image classifiers [109], [110], similarity to neighbours [101], [102] or to class prototypes [98], [111].”
MethodAdapting Object Detectors via Selective Cross-Domain Alignment
Zhu, X., Pang, J., Yang, C., Shi, J., & Lin, D. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00078 · Cited by 387
Exploring Categorical Regularization for Domain Adaptive Object Detection
Xu, C.-D., Zhao, X.-R., Jin, X., & Wei, X.-S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01174 · Cited by 355
Tommasi, T., Patricia, N., Caputo, B., & Tuytelaars, T. (2017) · Advances in Computer Vision and Pattern Recognition · doi:10.1007/978-3-319-58347-1_2 · Cited by 245
Learning Aligned Cross-Modal Representations from Weakly Aligned Data
Castrejon, L., Aytar, Y., Vondrick, C., Pirsiavash, H., & Torralba, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.321 · Cited by 188
Fine-Grained Recognition in the Wild: A Multi-task Domain Adaptation Approach
Gebru, T., Hoffman, J., & Fei-Fei, L. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.151 · Cited by 152 · cited 1×
“On the other hand, domain confusion can be achieved either with adversarial losses such as GAN loss [38]–[40] and domain confusion loss [41], [42], or by using a domain classifier and gradient reversal layer (GRL) [43], [44].”
Background
Cited by
Yang, B., Lei, Y., Jia, F., & Xing, S. (2019) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2018.12.051 · Cited by 879
Transfer adaptation learning: A decade survey
Zhang, L., & Gao, X. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3183326 · Cited by 314
An adaptive deep transfer learning method for bearing fault diagnosis
Wu, Z., Jiang, H., Zhao, K., & Li, X. (2020) · Measurement · doi:10.1016/j.measurement.2019.107227 · Cited by 291
Li, J., Zi, S., Song, R., Li, Y., Hu, Y., & Du, Q. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3152587 · Cited by 64
“UDA methods can be roughly divided into adversarial learning-based, self-learning-based, and image-to-image translation-based [14].”
Background
Metadata
- Authors
- Csurka, G.
- Venue
- 2020 22nd International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)
- Publisher
- IEEE
- Published
- 2020-09
- Pages
- 1-8
- OpenAlex
- W3116546446
- Cited by
- 52
- References
- 25
- FWCI
- 4.54
- 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.