Progressive Domain Expansion Network for Single Domain Generalization
Open accessThe DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.
Abstract
Single domain generalization is a challenging case of model generalization, where the models are trained on a single domain and tested on other unseen domains. A promising solution is to learn cross-domain invariant representations by expanding the coverage of the training domain. These methods have limited generalization performance gains in practical applications due to the lack of appropriate safety and effectiveness constraints. In this paper, we propose a novel learning framework called progressive domain expansion network (PDEN) for single domain generalization. The domain expansion subnetwork and representation learning subnetwork in PDEN mutually benefit from each other by joint learning. For the domain expansion subnetwork, multiple domains are progressively generated in order to simulate various photometric and geometric transforms in unseen domains. A series of strategies are introduced to guarantee the safety and effectiveness of the expanded domains. For the domain invariant representation learning subnetwork, contrastive learning is introduced to learn the domain invariant representation in which each class is well clustered so that a better decision boundary can be learned to improve it’s generalization. Extensive experiments on classification and segmentation have shown that PDEN can achieve up to 15.28% improvement compared with the state-of-the-art single-domain generalization methods. Codes will be released soon at https://github.com/lileicv/PDEN
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
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 12×
“We observed that our method performs much better than other methods on SVHN, MNIST-M and USPS.”
InfluentialUnpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,395
Auto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067 · cited 1×
“G can be a variety of structures depending on related downstream tasks, such as AutoEncoder [18], HRNet [37], spatial transform network(STN) [15] or a combination of these networks.”
BackgroundDistilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204 · cited 1×
“In recent years, many domain adaptation methods [10, 30, 36, 9] have been proposed to solve the problem of domain drift between source and target domain, including feature-based adaptation[10], instancebased adaptation [6] and model parameter based adaptation [14].”
A Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714 · cited 3×
“In AdaIN, there are two fully-connected layers Lfc1, Lfc2: AdaIN(z, n) = Lfc1(n) z − μ(z) σ(z) + Lfc2(n) G(x, n) = GD(AdaIN(GE(x), n)) (2) where n ∼ N(0, 1).”
MethodInfluentialA simple framework for contrastive learning of visual representations
Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020) · arXiv · doi:10.48550/arxiv.2002.05709 · Cited by 10,857 · cited 1×
“SimCLR[3] generates positive pairs by imposing strong augmentation on whole images.”
BackgroundRepresentation Learning with Contrastive Predictive Coding
Oord, A. V. D., Li, Y., & Vinyals, O. (2018) · arXiv · doi:10.48550/arxiv.1807.03748 · Cited by 6,242 · cited 2×
“LNCE is the InfoNCE loss[32] used for contrastive learning.”
MethodDeep High-Resolution Representation Learning for Human Pose Estimation
Sun, K., Xiao, B., Liu, D., & Wang, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00584 · Cited by 5,984 · cited 1×
“G can be a variety of structures depending on related downstream tasks, such as AutoEncoder [18], HRNet [37], spatial transform network(STN) [15] or a combination of these networks.”
BackgroundLearning 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 4×
“The domain adaptation method in deep learning is mainly to align the distribution of source domain and target domain, including two kinds of methods: MMD based adaptation method[39, 25] and adversarial based method[10].”
BackgroundMethodInfluential
Cited by
Generalizing to unseen domains: A survey on domain generalization
Wang, J., Lan, C., Liu, C., Ouyang, Y., Qin, T., Lu, W., Chen, Y., Zeng, W., & Yu, P. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2022.3178128 · Cited by 1,046
“[52] used adversarial training to generate domains instead of samples.”
MethodZhao, C., Zio, E., & Shen, W. (2024) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2024.109964 · Cited by 521
Single-Source Domain Expansion Network for Cross-Scene Hyperspectral Image Classification
Zhang, Y., Li, W., Sun, W., Tao, R., & Du, Q. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3243853 · Cited by 334
Causality-Inspired Single-Source Domain Generalization for Medical Image Segmentation
Ouyang, C., Chen, C., Li, S., Li, Z., Qin, C., Bai, W., & Rueckert, D. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3224067 · Cited by 260
Metadata
- Authors
- Li, L., Gao, K., Cao, J., Huang, Z., Weng, Y., Mi, X., Yu, Z., Li, X., & Xia, B.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 224-233
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3175956495
- Cited by
- 197
- References
- 45
- FWCI
- 14.93
- 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.