Pith. sign in

REVIEW 2 major objections 1 minor 117 references

CPCANet unrolls the Flury-Gautschi algorithm into neural layers to discover a shared subspace across domains for generalization.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · grok-4.3

2026-06-30 23:49 UTC pith:B5P5PCPW

load-bearing objection CPCANet unrolls Flury-Gautschi for CPCA in DG but may not preserve the shared subspace property under task loss. the 2 major comments →

arxiv 2605.05136 v3 pith:B5P5PCPW submitted 2026-05-06 cs.CV

CPCANet: Deep Unfolding Common Principal Component Analysis for Domain Generalization

Yu-Hsi Chen , Abd-Krim Seghouane This is my paper
classification cs.CV
keywords domain generalizationcommon principal component analysisdeep unfoldingFlury-Gautschi algorithminvariant subspacezero-shot transferout-of-distribution generalization
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper proposes CPCANet to solve domain generalization by explicitly learning a structured domain-invariant subspace from second-order statistics rather than relying only on invariant learning tricks or architecture changes. It converts the iterative Flury-Gautschi algorithm used in Common Principal Component Analysis into a stack of fully differentiable layers that can be trained end-to-end with any base network. This integration is meant to force the model to find components that are common across training domains while keeping the solution interpretable and free of per-dataset adjustments. A reader would care because real-world data often arrives from unseen distributions, and the method offers a direct statistical route to robustness that stays architecture-agnostic. On four standard benchmarks the approach reaches state-of-the-art zero-shot transfer results.

Core claim

CPCANet unrolls the iterative Flury-Gautschi algorithm for Common Principal Component Analysis into fully differentiable neural layers. This integrates the statistical properties of CPCA into an end-to-end trainable framework, enforcing the discovery of a shared subspace across diverse domains while preserving interpretability. The resulting model is architecture-agnostic and requires no dataset-specific tuning, achieving state-of-the-art performance in zero-shot transfer on four standard domain generalization benchmarks.

What carries the argument

Unrolled Flury-Gautschi layers that embed Common Principal Component Analysis to extract a common subspace from multiple domains.

Load-bearing premise

Unrolling the Flury-Gautschi algorithm into neural layers will enforce discovery of a shared subspace across diverse domains while preserving interpretability and without requiring dataset-specific tuning.

What would settle it

A new domain generalization benchmark where CPCANet fails to match or exceed existing methods in zero-shot accuracy, or where the method needs per-dataset hyperparameter changes to reach its reported performance.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • State-of-the-art zero-shot transfer on four standard DG benchmarks
  • Compatible with any base neural architecture without modification
  • No dataset-specific tuning required
  • Interpretability retained through the CPCA statistical foundation

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Unrolling other iterative statistical procedures could yield similar plug-in modules for distribution-shift problems.
  • Placing the layers at multiple depths might capture common structure at different scales of abstraction.
  • Testing on domains with unequal sample sizes would check whether the common subspace remains stable under imbalance.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

2 major / 1 minor

Summary. The paper proposes CPCANet, which unrolls the iterative Flury-Gautschi algorithm for Common Principal Component Analysis (CPCA) into fully differentiable neural layers. This is claimed to integrate CPCA's statistical properties into an end-to-end trainable framework for domain generalization, enforcing discovery of a shared invariant subspace across domains. The method is presented as architecture-agnostic with no dataset-specific tuning, and experiments report state-of-the-art zero-shot transfer performance on four standard DG benchmarks.

Significance. If the unrolling preserves the CPCA common-eigenvector property under task-driven training and the reported gains are reproducible, the work would offer a principled way to inject second-order statistical invariance into deep DG models while retaining interpretability. This could complement existing invariant-feature approaches and reduce reliance on ad-hoc regularizers.

major comments (2)
  1. [Abstract (CPCANet framework paragraph)] The abstract asserts that the unrolled layers 'enforce the discovery of a shared subspace' and 'integrate the statistical properties of CPCA,' yet supplies no layer equations, fixed-point conditions, or constraint mechanisms. Without these, it is impossible to verify whether the output satisfies the CPCA definition of common eigenvectors across domain covariances when optimized only under downstream classification loss.
  2. [Method and Experiments] No derivation, ablation, or post-hoc verification is referenced showing that the learned mapping remains close to a CPCA solution (e.g., eigenvector alignment or subspace overlap metrics computed on held-out domain covariances). This directly bears on the central claim that the approach preserves CPCA guarantees rather than reducing to an arbitrary learned projection.
minor comments (1)
  1. [Abstract] The abstract states 'Code is available at https://github.com/wish44165/CPCANet' but provides no link to supplementary material containing the unrolled layer pseudocode or hyper-parameter settings used in the reported benchmarks.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript. We address the two major comments below and outline the revisions we will make to strengthen the presentation of the CPCANet framework and its connection to CPCA.

read point-by-point responses

  1. Referee: [Abstract (CPCANet framework paragraph)] The abstract asserts that the unrolled layers 'enforce the discovery of a shared subspace' and 'integrate the statistical properties of CPCA,' yet supplies no layer equations, fixed-point conditions, or constraint mechanisms. Without these, it is impossible to verify whether the output satisfies the CPCA definition of common eigenvectors across domain covariances when optimized only under downstream classification loss.

    Authors: We agree the abstract is intentionally concise and does not contain equations. The unrolling of the Flury-Gautschi algorithm, including the per-iteration updates for common eigenvectors and the fixed-point behavior, is derived in Section 3.1–3.2 of the manuscript. The differentiable layers are constructed so that each forward pass approximates one iteration of the original algorithm; the shared subspace is therefore a structural property of the architecture rather than an emergent effect of the loss alone. We will revise the abstract to include a one-sentence pointer to these sections and a brief mention of the fixed-point iteration. revision: yes

  2. Referee: [Method and Experiments] No derivation, ablation, or post-hoc verification is referenced showing that the learned mapping remains close to a CPCA solution (e.g., eigenvector alignment or subspace overlap metrics computed on held-out domain covariances). This directly bears on the central claim that the approach preserves CPCA guarantees rather than reducing to an arbitrary learned projection.

    Authors: The manuscript provides the algorithmic derivation of the unrolled layers in Section 3 and the supplementary material. However, we did not include quantitative post-training verification (e.g., eigenvector alignment or Grassmann distance to a separately computed CPCA solution on held-out covariances) or corresponding ablations. We will add these analyses in a new subsection of the experiments, together with an ablation on the number of unrolled iterations, to demonstrate that the learned mapping stays close to the CPCA fixed point. revision: yes

Circularity Check

0 steps flagged

No significant circularity; unrolling of FG algorithm is self-contained

full rationale

The paper's core contribution is the unrolling of the established Flury-Gautschi iterative algorithm for CPCA into differentiable layers, presented as a direct integration of existing statistical properties into an end-to-end framework. No self-definitional loops, fitted inputs renamed as predictions, or load-bearing self-citations appear in the derivation chain. The claim that the layers enforce a shared subspace follows from the unrolling construction itself rather than reducing to a fit or prior author result by definition. The derivation remains independent of the target DG performance metrics and does not rely on renaming known patterns or smuggling ansatzes via citation.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available, so no concrete free parameters, axioms, or invented entities can be extracted. The central claim rests on the unstated premise that the statistical properties of CPCA survive the unrolling process and produce a genuinely domain-invariant subspace.

pith-pipeline@v0.9.1-grok · 5715 in / 1287 out tokens · 20181 ms · 2026-06-30T23:49:57.617491+00:00 · methodology

0 comments
read the original abstract

Domain Generalization (DG) aims to learn representations that remain robust under out-of-distribution (OOD) shifts and generalize effectively to unseen target domains. While recent invariant learning strategies and architectural advances have achieved strong performance, explicitly discovering a structured domain-invariant subspace through second-order statistics remains underexplored. In this work, we propose CPCANet, a novel framework grounded in Common Principal Component Analysis (CPCA), which unrolls the iterative Flury-Gautschi (FG) algorithm into fully differentiable neural layers. This approach integrates the statistical properties of CPCA into an end-to-end trainable framework, enforcing the discovery of a shared subspace across diverse domains while preserving interpretability. Experiments on four standard DG benchmarks demonstrate that CPCANet achieves state-of-the-art (SOTA) performance in zero-shot transfer. Moreover, CPCANet is architecture-agnostic and requires no dataset-specific tuning, providing a simple and efficient approach to learning robust representations under distribution shift. Code is available at https://github.com/wish44165/CPCANet.

Review history (2 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

117 extracted references · 6 canonical work pages · 2 internal anchors

  1. [1]

    Absil, R

    P.-A. Absil, R. Mahony, and R. Sepulchre.Optimization algorithms on matrix manifolds. Princeton University Press, 2008. 9

    2008

  2. [2]

    Ahuja, E

    K. Ahuja, E. Caballero, D. Zhang, J.-C. Gagnon-Audet, Y . Bengio, I. Mitliagkas, and I. Rish. Invariance principle meets information bottleneck for out-of-distribution generalization.Ad- vances in Neural Information Processing Systems, 34:3438–3450, 2021

    2021

  3. [3]

    Y . An, Z. Wang, X. Chen, and H. Zhang. Du2stdnet: A deep unfolding network for underwater small target detection.Ocean Engineering, 350:124200, 2026

    2026

  4. [4]

    Arpit, H

    D. Arpit, H. Wang, Y . Zhou, and C. Xiong. Ensemble of averages: Improving model selec- tion and boosting performance in domain generalization.Advances in Neural Information Processing Systems, 35:8265–8277, 2022

    2022

  5. [5]

    Bagnato and A

    L. Bagnato and A. Punzo. Unconstrained representation of orthogonal matrices with application to common principal components.Computational Statistics, 36(2):1177–1195, 2021

    2021

  6. [6]

    Balaji, S

    Y . Balaji, S. Sankaranarayanan, and R. Chellappa. Metareg: Towards domain generalization using meta-regularization.Advances in neural information processing systems, 31, 2018

    2018

  7. [7]

    Balatsoukas-Stimming and C

    A. Balatsoukas-Stimming and C. Studer. Deep unfolding for communications systems: A survey and some new directions. In2019 IEEE International Workshop on Signal Processing Systems (SiPS), pages 266–271. IEEE, 2019

    2019

  8. [8]

    P. L. Bartlett, A. Montanari, and A. Rakhlin. Deep learning: a statistical viewpoint.Acta numerica, 30:87–201, 2021

    2021

  9. [9]

    Beck and M

    A. Beck and M. Teboulle. A fast iterative shrinkage-thresholding algorithm with application to wavelet-based image deblurring. In2009 IEEE international conference on acoustics, speech and signal processing, pages 693–696. IEEE, 2009

    2009

  10. [10]

    Beery, G

    S. Beery, G. Van Horn, and P. Perona. Recognition in terra incognita. InProceedings of the European conference on computer vision (ECCV), pages 456–473, 2018

    2018

  11. [11]

    Ben-David, J

    S. Ben-David, J. Blitzer, K. Crammer, and F. Pereira. Analysis of representations for domain adaptation.Advances in neural information processing systems, 19, 2006

    2006

  12. [12]

    Boente and L

    G. Boente and L. Orellana. A robust approach to common principal components.Statistics in Genetics and in the Environmental Sciences, pages 117–145, 2001

    2001

  13. [13]

    Boente, A

    G. Boente, A. M. Pires, and I. M. Rodrigues. Influence functions and outlier detection under the common principal components model: A robust approach.Biometrika, 89(4):861–875, 2002

    2002

  14. [14]

    J. Cha, S. Chun, K. Lee, H.-C. Cho, S. Park, Y . Lee, and S. Park. Swad: Domain generalization by seeking flat minima.Advances in Neural Information Processing Systems, 34:22405–22418, 2021

    2021

  15. [15]

    J. Cha, K. Lee, S. Park, and S. Chun. Domain generalization by mutual-information regular- ization with pre-trained models. InEuropean conference on computer vision, pages 440–457. Springer, 2022

    2022

  16. [16]

    B. Chen, Z. Du, and Y . Yang. Snapshot-similarity-guided sparse unfolding transformer for accurate doa estimation.Signal Processing, page 110645, 2026

    2026

  17. [17]

    G. Cybenko. Approximation by superpositions of a sigmoidal function.Mathematics of control, signals and systems, 2(4):303–314, 1989

    1989

  18. [18]

    Daubechies, M

    I. Daubechies, M. Defrise, and C. De Mol. An iterative thresholding algorithm for linear inverse problems with a sparsity constraint.Communications on Pure and Applied Mathematics: A Journal Issued by the Courant Institute of Mathematical Sciences, 57(11):1413–1457, 2004

    2004

  19. [19]

    Dayal, V

    A. Dayal, V . KB, L. R. Cenkeramaddi, C. Mohan, A. Kumar, and V . N Balasubramanian. Madg: margin-based adversarial learning for domain generalization.Advances in Neural Information Processing Systems, 36:58938–58952, 2023. 10

    2023

  20. [20]

    S. Deka, K. Deka, N. T. Nguyen, S. Sharma, V . Bhatia, and N. Rajatheva. Comprehensive review of deep unfolding techniques for next-generation wireless communication systems. IEEE Internet of Things Journal, 2026

    2026

  21. [21]

    Demirel, E

    B. Demirel, E. Aptoula, and H. Ozkan. Adrmx: Additive disentanglement of domain features with remix loss.arXiv preprint arXiv:2308.06624, 2023

    work page arXiv 2023

  22. [22]

    L. Deng, Q. Liu, G. Xu, and H. Zhu. Dusrnet: Deep unfolding sparse-regularized network for infrared small target detection.Infrared Physics & Technology, 146:105727, 2025

    2025

  23. [23]

    Y . Du, J. Xu, H. Xiong, Q. Qiu, X. Zhen, C. G. Snoek, and L. Shao. Learning to learn with variational information bottleneck for domain generalization. InEuropean conference on computer vision, pages 200–216. Springer, 2020

    2020

  24. [24]

    T. Duras. The fixed effects pca model in a common principal component environment. Communications in Statistics-Theory and Methods, 51(6):1653–1673, 2022

    2022

  25. [25]

    Eastwood, A

    C. Eastwood, A. Robey, S. Singh, J. V on Kügelgen, H. Hassani, G. J. Pappas, and B. Schölkopf. Probable domain generalization via quantile risk minimization.Advances in Neural Informa- tion Processing Systems, 35:17340–17358, 2022

    2022

  26. [26]

    Edelman, T

    A. Edelman, T. A. Arias, and S. T. Smith. The geometry of algorithms with orthogonality constraints.SIAM journal on Matrix Analysis and Applications, 20(2):303–353, 1998

    1998

  27. [27]

    C. Fang, Y . Xu, and D. N. Rockmore. Unbiased metric learning: On the utilization of multiple datasets and web images for softening bias. InProceedings of the IEEE international conference on computer vision, pages 1657–1664, 2013

    2013

  28. [28]

    B. Feng, C. Feng, K.-K. Wong, and T. Q. Quek. Deep unfolding neural networks for fluid antenna-enhanced vehicular communication.IEEE Transactions on Vehicular Technology, 2025

    2025

  29. [29]

    B. K. Flury. Two generalizations of the common principal component model.Biometrika, 74(1):59–69, 1987

    1987

  30. [30]

    B. N. Flury. Common principal components in k groups.Journal of the American Statistical Association, 79(388):892–898, 1984

    1984

  31. [31]

    B. N. Flury and W. Gautschi. An algorithm for simultaneous orthogonal transformation of several positive definite symmetric matrices to nearly diagonal form.SIAM Journal on Scientific and Statistical Computing, 7(1):169–184, 1986

    1986

  32. [32]

    Ganin, E

    Y . Ganin, E. Ustinova, H. Ajakan, P. Germain, H. Larochelle, F. Laviolette, M. March, and V . Lempitsky. Domain-adversarial training of neural networks.Journal of machine learning research, 17(59):1–35, 2016

    2016

  33. [33]

    Gregor and Y

    K. Gregor and Y . LeCun. Learning fast approximations of sparse coding. InProceedings of the 27th international conference on international conference on machine learning, pages 399–406, 2010

    2010

  34. [34]

    Gu and H

    F. Gu and H. Wu. Raw data maximum likelihood estimation for common principal component models: A state space approach.psychometrika, 81(3):751–773, 2016

    2016

  35. [35]

    Gulrajani and D

    I. Gulrajani and D. Lopez-Paz. In search of lost domain generalization. InInternational Conference on Learning Representations, 2021

    2021

  36. [36]

    J. Guo, L. Qi, Y . Shi, and Y . Gao. Start: A generalized state space model with saliency- driven token-aware transformation.Advances in Neural Information Processing Systems, 37:55286–55313, 2024

    2024

  37. [37]

    J. Guo, N. Wang, L. Qi, and Y . Shi. Aloft: A lightweight mlp-like architecture with dy- namic low-frequency transform for domain generalization. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 24132–24141, 2023. 11

    2023

  38. [38]

    K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770– 778, 2016

    2016

  39. [39]

    J. R. Hershey, J. L. Roux, and F. Weninger. Deep unfolding: Model-based inspiration of novel deep architectures.arXiv preprint arXiv:1409.2574, 2014

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  40. [40]

    Hornik, M

    K. Hornik, M. Stinchcombe, and H. White. Multilayer feedforward networks are universal approximators.Neural networks, 2(5):359–366, 1989

    1989

  41. [41]

    Q. Hou, Z. Jiang, L. Yuan, M.-M. Cheng, S. Yan, and J. Feng. Vision permutator: A permutable mlp-like architecture for visual recognition.IEEE transactions on pattern analysis and machine intelligence, 45(1):1328–1334, 2022

    2022

  42. [42]

    Q. Hu, Y . Cai, Q. Shi, K. Xu, G. Yu, and Z. Ding. Iterative algorithm induced deep-unfolding neural networks: Precoding design for multiuser mimo systems.IEEE Transactions on Wireless Communications, 20(2):1394–1410, 2020

    2020

  43. [43]

    S. Hu, J. Ruan, N. Langer, J. Bosch-Bayard, Z. Lv, D. Yao, and P. A. Valdes-Sosa. Spec- tral homogeneity cross frequencies can be a quality metric for the large-scale resting eeg preprocessing.arXiv preprint arXiv:2310.11994, 2023

    work page arXiv 2023

  44. [44]

    Averaging Weights Leads to Wider Optima and Better Generalization

    P. Izmailov, D. Podoprikhin, T. Garipov, D. Vetrov, and A. G. Wilson. Averaging weights leads to wider optima and better generalization, 2019.arXiv preprint arXiv:1803.05407, 1803

    work page internal anchor Pith review Pith/arXiv arXiv 2019

  45. [45]

    S. Jeon, K. Hong, P. Lee, J. Lee, and H. Byun. Feature stylization and domain-aware contrastive learning for domain generalization. InProceedings of the 29th ACM international conference on multimedia, pages 22–31, 2021

    2021

  46. [46]

    Jiang and V

    Y . Jiang and V . Veitch. Invariant and transportable representations for anti-causal domain shifts.Advances in Neural Information Processing Systems, 35:20782–20794, 2022

    2022

  47. [47]

    Kanaan-Izquierdo, A

    S. Kanaan-Izquierdo, A. Ziyatdinov, and A. Perera-Lluna. Multiview and multifeature spectral clustering using common eigenvectors.Pattern Recognition Letters, 102:30–36, 2018

    2018

  48. [48]

    D. Kim, Y . Yoo, S. Park, J. Kim, and J. Lee. Selfreg: Self-supervised contrastive regularization for domain generalization. InProceedings of the IEEE/CVF international conference on computer vision, pages 9619–9628, 2021

    2021

  49. [49]

    S. Kong, W. Wang, X. Feng, and X. Jia. Deep red unfolding network for image restoration. IEEE Transactions on Image Processing, 31:852–867, 2021

    2021

  50. [50]

    Krishnamachari, S.-K

    K. Krishnamachari, S.-K. Ng, and C.-S. Foo. Uniformly distributed feature representations for fair and robust learning.Transactions on Machine Learning Research, 2024

    2024

  51. [51]

    Lezcano-Casado and D

    M. Lezcano-Casado and D. Martınez-Rubio. Cheap orthogonal constraints in neural networks: A simple parametrization of the orthogonal and unitary group. InInternational Conference on Machine Learning, pages 3794–3803. PMLR, 2019

    2019

  52. [52]

    B. Li, Y . Shen, J. Yang, Y . Wang, J. Ren, T. Che, J. Zhang, and Z. Liu. Sparse mixture- of-experts are domain generalizable learners. InThe Eleventh International Conference on Learning Representations, 2023

    2023

  53. [53]

    D. Li, Y . Yang, Y .-Z. Song, and T. Hospedales. Learning to generalize: Meta-learning for domain generalization. InProceedings of the AAAI conference on artificial intelligence, volume 32, 2018

    2018

  54. [54]

    D. Li, Y . Yang, Y .-Z. Song, and T. M. Hospedales. Deeper, broader and artier domain generalization. InProceedings of the IEEE international conference on computer vision, pages 5542–5550, 2017

    2017

  55. [55]

    H. Li. Multivariate time series clustering based on common principal component analysis. Neurocomputing, 349:239–247, 2019. 12

    2019

  56. [56]

    H. Li, S. J. Pan, S. Wang, and A. C. Kot. Domain generalization with adversarial feature learning. InProceedings of the IEEE conference on computer vision and pattern recognition, pages 5400–5409, 2018

    2018

  57. [57]

    H. Li, Q. Yin, Y . Luo, N. Chen, Q. Ling, M. Li, and J. Yang. Small moving target detection of remote sensing video satellite based on deep unfolding network. In2025 4th International Conference on Electronic Information Technology (EIT), pages 584–588. IEEE, 2025

    2025

  58. [58]

    J. Li, F. Li, and S. Todorovic. Efficient riemannian optimization on the stiefel manifold via the cayley transform. InInternational Conference on Learning Representations, 2020

    2020

  59. [59]

    Y . Li, X. Tian, M. Gong, Y . Liu, T. Liu, K. Zhang, and D. Tao. Deep domain generalization via conditional invariant adversarial networks. InProceedings of the European conference on computer vision (ECCV), pages 624–639, 2018

    2018

  60. [60]

    J. Liu, Y . Han, X. Xiu, J. Zhang, and W. Liu. Lightweight deep unfolding networks with enhanced robustness for infrared small target detection.arXiv preprint arXiv:2509.08205, 2025

    work page arXiv 2025

  61. [61]

    P. Liu, L. Pang, J. Peng, Y . Luo, J. Liu, and X. Cao. Ctvnet: Gradient prior-guided deep unfolding network for infrared small target detection.IEEE Transactions on Geoscience and Remote Sensing, 63:1–14, 2025

    2025

  62. [62]

    P. Liu, J. Peng, Y . Luo, J. Fu, J. Li, and X. Cao. Ddfet: Infrared small target detection via a dual-domain fused deep unfolding network.IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2025

    2025

  63. [63]

    Y . Liu, Y . Tian, Y . Zhao, H. Yu, L. Xie, Y . Wang, Q. Ye, J. Jiao, and Y . Liu. Vmamba: Visual state space model.Advances in neural information processing systems, 37:103031–103063, 2024

    2024

  64. [64]

    S. Long, Q. Zhou, X. Li, X. Lu, C. Ying, Y . Luo, L. Ma, and S. Yan. Dgmamba: Domain generalization via generalized state space model. InProceedings of the 32nd ACM International Conference on Multimedia, pages 3607–3616, 2024

    2024

  65. [65]

    F. Lv, J. Liang, S. Li, B. Zang, C. H. Liu, Z. Wang, and D. Liu. Causality inspired representation learning for domain generalization. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 8046–8056, 2022

    2022

  66. [66]

    Q. Ma, J. Jiang, X. Liu, and J. Ma. Deep unfolding network for spatiospectral image super- resolution.IEEE Transactions on Computational Imaging, 8:28–40, 2021

    2021

  67. [67]

    Z. Ma, Á. López-Oriona, H. Ombao, and Y . Sun. Fcpca: Fuzzy clustering of high-dimensional time series based on common principal component analysis.International Journal of Approxi- mate Reasoning, page 109552, 2025

    2025

  68. [68]

    Z. Ma, Á. López-Oriona, H. Ombao, and Y . Sun. Robcpca: A robust multivariate time series clustering method based on common principal component analysis.Journal of Classification, pages 1–30, 2026

    2026

  69. [69]

    Mahajan, S

    D. Mahajan, S. Tople, and A. Sharma. Domain generalization using causal matching. In International conference on machine learning, pages 7313–7324. PMLR, 2021

    2021

  70. [70]

    Marivani, E

    I. Marivani, E. Tsiligianni, B. Cornelis, and N. Deligiannis. Multimodal deep unfolding for guided image super-resolution.IEEE Transactions on Image Processing, 29:8443–8456, 2020

    2020

  71. [71]

    C. Mou, Q. Wang, and J. Zhang. Deep generalized unfolding networks for image restoration. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 17399–17410, 2022

    2022

  72. [72]

    Muandet, D

    K. Muandet, D. Balduzzi, and B. Schölkopf. Domain generalization via invariant feature representation. InInternational conference on machine learning, pages 10–18. PMLR, 2013. 13

    2013

  73. [73]

    H. Nam, H. Lee, J. Park, W. Yoon, and D. Yoo. Reducing domain gap by reducing style bias. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 8690–8699, 2021

    2021

  74. [74]

    Nguyen, K

    T. Nguyen, K. Do, B. Duong, and T. Nguyen. Domain generalisation via risk distribution matching. InProceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 2790–2799, 2024

    2024

  75. [75]

    S. J. Pan and Q. Yang. A survey on transfer learning.IEEE Transactions on knowledge and data engineering, 22(10):1345–1359, 2009

    2009

  76. [76]

    P. T. Pepler.The identification and application of common principal components. PhD thesis, Stellenbosch: Stellenbosch University, 2014

    2014

  77. [77]

    Perez, F

    E. Perez, F. Strub, H. De Vries, V . Dumoulin, and A. Courville. Film: Visual reasoning with a general conditioning layer. InProceedings of the AAAI conference on artificial intelligence, volume 32, 2018

    2018

  78. [78]

    U. Riaz, F. A. Razzaq, S. Hu, and P. A. Valdés-Sosa. Stepwise covariance-free common principal components (cf-cpc) with an application to neuroscience.Frontiers in Neuroscience, 15:750290, 2021

    2021

  79. [79]

    C. J. Rozell, D. H. Johnson, R. G. Baraniuk, and B. A. Olshausen. Sparse coding via thresholding and local competition in neural circuits.Neural computation, 20(10):2526–2563, 2008

    2008

  80. [80]

    S. Shi, Y . Cai, Q. Hu, B. Champagne, and L. Hanzo. Deep-unfolding neural-network aided hybrid beamforming based on symbol-error probability minimization.IEEE Transactions on Vehicular Technology, 72(1):529–545, 2022

    2022

Showing first 80 references.