The DOI matches its Crossref record; 47 of the 47 references it cites were found in a registry or an index.
Reducing Domain Gap by Reducing Style Bias
Open accessAbstract
Convolutional Neural Networks (CNNs) often fail to maintain their performance when they confront new test domains, which is known as the problem of domain shift. Recent studies suggest that one of the main causes of this problem is CNNs’ strong inductive bias towards image styles (i.e. textures) which are sensitive to domain changes, rather than contents (i.e. shapes). Inspired by this, we propose to reduce the intrinsic style bias of CNNs to close the gap between domains. Our Style-Agnostic Networks (SagNets) disentangle style encodings from class categories to prevent style biased predictions and focus more on the contents. Extensive experiments show that our method effectively reduces the style bias and makes the model more robust under domain shift. It achieves remarkable performance improvements in a wide range of cross-domain tasks including domain generalization, unsupervised domain adaptation, and semi-supervised domain adaptation on multiple datasets.1
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 Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Pan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387
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
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
Johnson, J., Alahi, A., & Fei-Fei, L. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_43 · Cited by 11,283
Explaining and Harnessing Adversarial Examples
Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014) · arXiv · doi:10.48550/arxiv.1412.6572 · Cited by 10,381
Domain-Adversarial Training of Neural Networks
Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., & Lempitsky, V. (2017) · Advances in Computer Vision and Pattern Recognition · doi:10.1007/978-3-319-58347-1_10 · Cited by 8,318
Image Style Transfer Using Convolutional Neural Networks
Gatys, L. A., Ecker, A. S., & Bethge, M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.265 · Cited by 6,025
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
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
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
Miyato, T., Maeda, S.-I., Koyama, M., & Ishii, S. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2858821 · Cited by 2,843
CyCADA: 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 1×
“The mainstream approach is aligning the source and the target distributions by minimizing MMD [17, 35], adversarial learning [11, 46, 34], or image-level translation [22, 39].”
BackgroundDeep Hashing Network for Unsupervised Domain Adaptation
Venkateswara, H., Eusebio, J., Chakraborty, S., & Panchanathan, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.572 · Cited by 2,171
Analysis of Representations for Domain Adaptation
Ben-David, S., Blitzer, J., Crammer, K., & Pereira, F. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0022 · Cited by 2,019
Moment Matching for Multi-Source Domain Adaptation
Peng, X., Bai, Q., Xia, X., Huang, Z., Saenko, K., & Wang, B. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00149 · Cited by 1,621
Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F. A., & Brendel, W. (2018) · arXiv · doi:10.48550/arxiv.1811.12231 · Cited by 1,490 · cited 9×
“Geirhos et al. [14] observed that standard ImageNet-trained CNNs are likely to make a style-biased decision on ambiguous stimuli (e.g. images stylized to different categories).”
BackgroundMethodInfluentialBenchmarking Neural Network Robustness to Common Corruptions and Perturbations
Hendrycks, D., & Dietterich, T. (2019) · arXiv · doi:10.48550/arxiv.1903.12261 · Cited by 1,335
Conditional Adversarial Domain Adaptation
Long, M., Cao, Z., Wang, J., & Jordan, M. I. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.10667 · Cited by 1,281
Deeper, Broader and Artier Domain Generalization
Li, D., Yang, Y., Song, Y.-Z., & Hospedales, T. M. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.591 · Cited by 1,237
Domain Generalization with Adversarial Feature Learning
Li, H., Pan, S. J., Wang, S., & Kot, A. C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00566 · Cited by 1,213
The importance of shape in early lexical learning
Landau, B., Smith, L. B., & Jones, S. S. (1988) · Cognitive Development · doi:10.1016/0885-2014(88)90014-7 · Cited by 1,174
Domain Generalization by Solving Jigsaw Puzzles
Carlucci, F. M., D'Innocente, A., Bucci, S., Caputo, B., & Tommasi, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00233 · Cited by 813
MetaReg: towards domain generalization using meta-regularization
Balaji, Y., Sankaranarayanan, S., & Chellappa, R. (2018) · neural information processing systems · Cited by 805
Domain Generalization via Invariant Feature Representation
Muandet, K., Balduzzi, D., & Schölkopf, B. (2013) · arXiv · doi:10.48550/arxiv.1301.2115 · Cited by 771
Semi-Supervised Domain Adaptation via Minimax Entropy
Saito, K., Kim, D., Sclaroff, S., Darrell, T., & Saenko, K. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00814 · Cited by 680
Deep Domain Generalization via Conditional Invariant Adversarial Networks
Li, Y., Tian, X., Gong, M., Liu, Y., Liu, T., Zhang, K., & Tao, D. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01267-0_38 · Cited by 576
Image to Image Translation for Domain Adaptation
Murez, Z., Kolouri, S., Kriegman, D., Ramamoorthi, R., & Kim, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00473 · Cited by 540
Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization
Ghifary, M., Balduzzi, D., Kleijn, W. B., & Zhang, M. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2599532 · Cited by 471
Domain Adaptive Neural Networks for Object Recognition
Ghifary, M., Kleijn, W. B., & Zhang, M. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-13560-1_76 · Cited by 437
Episodic Training for Domain Generalization
Li, D., Zhang, J., Yang, Y., Liu, C., Song, Y.-Z., & Hospedales, T. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00153 · Cited by 435
Learning Semantic Representations for Unsupervised Domain Adaptation
Xie, S., Zheng, Z., Chen, L., & Chen, C. (2018) · International Conference on Machine Learning · Cited by 419
Generalisation in humans and deep neural networks
Geirhos, R., Temme, C. R. M., Rauber, J., Schütt, H. H., Bethge, M., & Wichmann, F. A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.08750 · Cited by 399
Domain Generalization via Model-Agnostic Learning of Semantic Features
Dou, Q., Castro, D. C., Kamnitsas, K., & Glocker, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.13580 · Cited by 381
SRM: A Style-Based Recalibration Module for Convolutional Neural Networks
Lee, H., Kim, H.-E., & Nam, H. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00194 · Cited by 351
Self-citationThe Origins and Prevalence of Texture Bias in Convolutional Neural NetworksPreprint
Hermann, K. L., Chen, T., & Kornblith, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.09071 · Cited by 349
Deep convolutional networks do not classify based on global object shape
Baker, N., Lu, H., Erlikhman, G., & Kellman, P. J. (2018) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1006613 · Cited by 345
Generalizing to Unseen Domains via Adversarial Data Augmentation
Volpi, R., Namkoong, H., Şener, O., Duchi, J. C., Murino, V., & Savarese, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.12018 · Cited by 343
Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet
Brendel, W., & Bethge, M. (2019) · arXiv · doi:10.48550/arxiv.1904.00760 · Cited by 323
On the Performance of GoogLeNet and AlexNet Applied to Sketches
Ballester, P., & Araujo, R. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10171 · Cited by 308
Domain Generalization Using a Mixture of Multiple Latent Domains
Matsuura, T., & Harada, T. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6846 · Cited by 289
Transfer between Picture Books and the Real World by Very Young Children
Ganea, P. A., Pickard, M. B., & DeLoache, J. S. (2008) · Journal of Cognition and Development · doi:10.1080/15248370701836592 · Cited by 286
Batch-Instance Normalization for Adaptively Style-Invariant Neural NetworksPreprint
Nam, H., & Kim, H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.07925 · Cited by 242
Self-citationSemi-supervised Domain Adaptation with Subspace Learning for visual recognition
Yao, T., Pan, Y., Ngo, C.-W., Li, H., & Mei, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298826 · Cited by 197
Semi-supervised Domain Adaptation with Instance Constraints
Donahue, J., Hoffman, J., Rodner, E., Saenko, K., & Darrell, T. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.92 · Cited by 180
Domain Generalization with Domain-Specific Aggregation Modules
D’Innocente, A., & Barbara Caputo, B. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-12939-2_14 · Cited by 128
Assessing Shape Bias Property of Convolutional Neural Networks
Hosseini, H., Xiao, B., Jaiswal, M. S., & Poovendran, R. (2018) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00258 · Cited by 43
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
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
SelfReg: Self-supervised Contrastive Regularization for Domain Generalization
Kim, D., Yoo, Y., Park, S., Kim, J., & Lee, J. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00948 · Cited by 262
Burgert, T., Stoll, O., Rota, P., & Demir, B. (2025) · arXiv · doi:10.48550/arxiv.2509.20234 · Cited by 5
Metadata
- Authors
- Nam, H., Lee, H., Park, J., Yoon, W., & Yoo, D.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 8686-8695
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3131549653
- Cited by
- 353
- References
- 47
- FWCI
- 29.12
- 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.