Domain Generalization for Object Recognition with Multi-task Autoencoders
Open accessAbstract
The problem of domain generalization is to take knowledge acquired from a number of related domains, where training data is available, and to then successfully apply it to previously unseen domains. We propose a new feature learning algorithm, Multi-Task Autoencoder (MTAE), that provides good generalization performance for cross-domain object recognition. The algorithm extends the standard denoising autoencoder framework by substituting artificially induced corruption with naturally occurring inter-domain variability in the appearance of objects. Instead of reconstructing images from noisy versions, MTAE learns to transform the original image into analogs in multiple related domains. It thereby learns features that are robust to variations across domains. The learnt features are then used as inputs to a classifier. We evaluated the performance of the algorithm on benchmark image recognition datasets, where the task is to learn features from multiple datasets and to then predict the image label from unseen datasets. We found that (denoising) MTAE outperforms alternative autoencoder-based models as well as the current state-of-the-art algorithms for domain generalization.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Rotated MNIST examples have dimension (1,28,28).
“Our dataset contains 70 , 000 examples of dimension (1 , 28 , 28) and 10 classes.”
From In Search of Lost Domain Generalization (2020) · cites this paper as [Ghifary et al., 2015]
The Data setup section says the MNIST-r digit images were subsampled to 16 × 16, not 28 × 28. It assigns 28 × 28 to the ETH80-p images instead. (LLM, conf=0.91)
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredOur Rotated MNIST dataset contains 70,000 examples.
“Our dataset contains 70 , 000 examples of dimension (1 , 28 , 28) and 10 classes.”
From In Search of Lost Domain Generalization (2020) · cites this paper as [Ghifary et al., 2015]
The Data setup section describes MNIST-r as six views of the same 1,000 selected images, yielding 6,000 examples rather than 70,000. It also says the images were subsampled to 16 × 16, not 28 × 28; the ten-class detail matches. (LLM, conf=0.90)
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredRotated MNIST has 10 classes.
“Our dataset contains 70 , 000 examples of dimension (1 , 28 , 28) and 10 classes.”
From In Search of Lost Domain Generalization (2020) · cites this paper as [Ghifary et al., 2015]
Rotated MNIST is a variant of MNIST where domain d ∈ {0, 15, 30, 45, 60, 75} contains digits rotated by d degrees.
“Rotated MNIST [Ghifary et al., 2015] is a variant of MNIST where domain d ∈ { 0, 15, 30, 45, 60, 75 } contains digits rotated by d degrees.”
From In Search of Lost Domain Generalization (2020) · cites this paper as [Ghifary et al., 2015]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
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 · see citing works
The Pascal Visual Object Classes Challenge: A Retrospective
Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-014-0733-5 · Cited by 7,139 · see citing works
Caruana, R. (1997) · Machine Learning · doi:10.1023/a:1007379606734 · Cited by 6,636 · see citing works
Greedy layer-wise training of deep networks
Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0024 · Cited by 4,841 · see citing works
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., & Darrell, T. (2013) · arXiv · doi:10.48550/arxiv.1310.1531 · Cited by 4,019 · see citing works
Adapting 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 · see citing works
Torralba, A., & Efros, A. A. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995347 · Cited by 2,440 · see citing works
Domain Generalization via Invariant Feature Representation
Muandet, K., Balduzzi, D., & Schölkopf, B. (2013) · arXiv · doi:10.48550/arxiv.1301.2115 · Cited by 771 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 28
- A. Argyriou, T. Evgeniou, and M. Pontil. Convex Multi-Task Feature Learning. Machine Learning, 73(3):243-272, 2008.
- M. Baktashmotlagh, M. T. Harandi, B. C. Lovell, and M. Salzmann. Domain Adaptation on the Statistical Man- ifold. In CVPR, pages 2481-2488, 2014.
- J. Baxter. A Model of Inductive Bias Learning. Journal of Artificial Intelligence Research, 12:149-198, 2000.
- Y. Bengio, A. C. Courville, and P. Vincent. Representa- tion Learning: A Review and New Perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(8):1798-1828, 2013.
- G. Blanchard, G. Lee, and C. Scott. Generalizing from Sev- eral Related Classification Tasks to a New Unlabeled Sam- ple. In NIPS, volume 1, pages 2178-2186, 2011.
- M. Chen, Z. Xu, K. Weinberger, and F. Sha. Marginalized Denoising Autoencoders for Domain Adaptation. In ICML, pages 767-774, 2012.
- M. J. Choi, J. J. Lim, A. Torralba, and A. S. Willsky. Ex- ploiting hierarchical context on a large database of object categories. In CVPR, pages 129-136, 2010.
- D. Ciresan, U. Meier, and J. Schmidhuber. Multi-column deep neural network for image classification. In CVPR, pages 3642-3649, 2012.
- K. Crammer and Y. Singer. On the algorithmic implemen- tation of multiclass kernel-based vector machines. JMLR, 2:265-292, 2001.
- R.-E. Fan, K.-W. Chang, C.-J. Hsieh, X.-R. Wang, and C.-J. Lin. LIBLINEAR: A Library for Large Linear Classification. JMLR, 9:1871-1874, 2008.
- C. Fang, Y. Xu, and D. N. Rockmore. Unbiased Metric Learning: On the Utilization of Multiple Datasets and Web Images for Softening Bias. In ICCV, pages 1657-1664, 2013.
- M. Ghifary, W. B. Kleijn, and M. Zhang. Deep hybrid networks with good out-of-sample object recognition. In ICASSP, pages 5437-5441, 2014.
- B. Gong, K. Grauman, and F. Sha. Reshaping Visual Datasets for Domain Adaptation. In NIPS, pages 1286-1294, 2013.
- B. Gong, Y. Shi, F. Sha, and K. Grauman. Geodesic Flow Kernel for Unsupervised Domain Adaptation. In CVPR, pages 2066-2073, 2012.
- A. Khosla, T. Zhou, T. Malisiewicz, A. Efros, and A. Tor- ralba. Undoing the Damage of Dataset Bias. In ECCV, vol- ume I, pages 158-171, 2012.
- A. Krizhevsky. Learning Multiple Layers of Features from Tiny Images. Master's thesis, Department of Computer Sci- ence, University of Toronto, Apr. 2009.
- Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient- based learning applied to document recognition. In Proceed- ings of the IEEE, volume 86, pages 2278-2324, 1998.
- B. Leibe and B. Schiele. Analyzing appearance and contour based methods for object categorization. In CVPR, pages 409-415, 2003.
- S. Rifai, P. Vincent, X. Muller, X. Glorot, and Y. Bengio. Contractive Auto-Encoders : Explicit Invariance During Fea- ture Extraction. In ICML, number 1, pages 833-840, 2011.
- D. Rumelhart, G. Hinton, and R. Williams. Parallel Dis- tributed Processing. I: Foundations. MIT Press, 1986.
- B. C. Russell, A. Torralba, K. P. Murphy, and W. T. Free- man. LabelMe: A database and web-based tool for image annotation. In IJCV, volume 77, pages 157-173. 2008.
- K. Saenko, B. Kulis, M. Fritz, and T. Darrell. Adapting Vi- sual Cateogry Models to New Domains. In ECCV, pages 213-226, 2010.
- I. Sutskever, O. Vinyals, and Q. Le. Sequence to Sequence Learning with Neural Networks. In NIPS, 2014.
- Y. Tang and C. Eliasmith. Deep networks for robust visual recognition. In ICML, pages 1055-1062, 2010.
- S. Thrun. Is learning the n-th thing any easier than learning the first? In NIPS, pages 640-646, 1996.
- P. Vincent, H. Larochelle, Y. Bengio, and P.-A. Manzagol. Extracting and Composing Robust Features with Denoising Autoencoders. In ICML, 2008.
- P. Vincent, H. Larochelle, I. Lajoie, Y. Bengio, and P.-A. Manzagol. Stacked Denoising Autoencoders: Learning Use- ful Representations in a Deep Network with a Local De- noising Criterion. Journal of Machine Learning Research, 11:3371-3408, 2010.
- Z. Xu, W. Li, L. Niu, and D. Xu. Exploiting Low-Rank Structure from Latent Domains for Domain Generalization. In ECCV, pages 628-643, 2014.
Cited by
Sorted by citations
Deep visual domain adaptation: A survey
Wang, M., & Deng, W. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.05.083 · Cited by 2,209 · see citing works
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 · see citing works
A 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 · see citing works
Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond
Feder, A., Keith, K. A., Manzoor, E., Pryzant, R., Sridhar, D., Wood-Doughty, Z., Eisenstein, J., Grimmer, J., Reichart, R., Roberts, M. E., et al. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00511 · Cited by 220 · see citing works
Triguero, I., Molina, D., Poyatos, J., Del Ser, J., & Herrera, F. (2024) · Information Fusion · doi:10.1016/j.inffus.2023.102135 · Cited by 90 · see citing works
In Search of Lost Domain Generalization
Gulrajani, I., & Lopez-Paz, D. (2020) · arXiv · doi:10.48550/arxiv.2007.01434 · Cited by 440 · see citing works
“Using all available data In Rotated MNIST, whereas the usual version of the dataset constructs all domains from the same set of 1000 digits, we divide all the MNIST digits evenly among domains.”
BackgroundMethodInfluentialDomain Generalization for Activity Recognition via Adaptive Feature Fusion
Qin, X., Wang, J., Chen, Y., Lu, W., & Jiang, X. (2023) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3552434 · Cited by 55 · see citing works
- Authors
- Ghifary, M., Kleijn, W. B., Zhang, M., & Balduzzi, D.
- Affiliations
- Victoria University of Wellington (NZ)
- Venue
- 2015 IEEE International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2015-12
- Pages
- 2551-2559
- OpenAlex
- W1920962657
- Cited by
- 664
- References
- 8
- Citations by year
- 2026: 8 · 2025: 61 · 2024: 66 · 2023: 96 · 2022: 82 · 2021: 122 · 2020: 102 · 2019: 62 · 2018: 34 · 2017: 19 · 2016: 11 · 2015: 1
- FWCI
- 12.21
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- domain generalization, denoising autoencoder, representation learning, domain-invariant features, unseen domains, image classification
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
