Improving Pseudo-Multiview Learning via Dual-Sampler Bidirectional Feature Flow
- 1Department of Computer Engineering, Korea National University of Transportation, Chungbuk 27469, Republic of Korea
Abstract
Pseudo-multiview learning (PML) improves classification by generating complementary internal representations and fusing their evidence using subjective logic. However, conventional PML incurs substantial computational costs as the number of pseudo-views increases. Multiscale grid-based PML alleviates this issue by generating lower-resolution pseudo-views through downsampling and integrating cross-scale features. Nevertheless, its unidirectional top-down feature flow is vulnerable to noise in high-resolution branches, which can propagate to lower-resolution branches and degrade classification performance. This paper proposes a noise-resilient multiscale PML framework. The proposed dual-sampler module enables each branch to aggregate complementary features from both higher- and lower-resolution branches, thereby establishing bidirectional cross-scale information flow. In addition, a noise-aware spatial-channel attention module jointly models feature discriminativeness and reliability, suppressing corrupted spatial regions and feature channels during cross-scale fusion. Experimental results on real-world datasets from diverse domains, including BreakHis at 40×, 100×, 200×, and 400× magnifications, Oxford-IIIT Pet, and Chest X-ray, demonstrate the superiority of the proposed method over baseline models in classification accuracy, convergence stability, and robustness to cross-scale Gaussian noise.
Related
- Is In-Context Reinforcement Learning A Posterior Sampler? An Empirical Study
- Learning Bidirectional Causal Interactions with Heteroscedastic Neural Networks
- Improving Learning of Green's Functions Through Kernel Decomposition
- Flexible latent variable models on graphs: Laplace approximated inference for multiview network data
- Improving Reduced-Order Rotating Detonation Engine Models with Data Assimilation and Machine Learning
BibTeX
@article{ngo2026improving,
title = {{Improving Pseudo-Multiview Learning via Dual-Sampler Bidirectional Feature Flow}},
author = {Dat Ngo},
journal = {Mathematics},
year = {2026},
month = nov,
doi = {10.3390/math14214001},
url = {https://www.mdpi.com/2227-7390/14/21/4001},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Improving Pseudo-Multiview Learning via Dual-Sampler Bidirectional Feature Flow
AU - Dat Ngo
PY - 2026
DA - 2026/11/02
JO - Mathematics
DO - 10.3390/math14214001
UR - https://www.mdpi.com/2227-7390/14/21/4001
AB - Pseudo-multiview learning (PML) improves classification by generating complementary internal representations and fusing their evidence using subjective logic. However, conventional PML incurs substantial computational costs as the number of pseudo-views increases. Multiscale grid-based PML alleviates this issue by generating lower-resolution pseudo-views through downsampling and integrating cross-scale features. Nevertheless, its unidirectional top-down feature flow is vulnerable to noise in high-resolution branches, which can propagate to lower-resolution branches and degrade classification performance. This paper proposes a noise-resilient multiscale PML framework. The proposed dual-sampler module enables each branch to aggregate complementary features from both higher- and lower-resolution branches, thereby establishing bidirectional cross-scale information flow. In addition, a noise-aware spatial-channel attention module jointly models feature discriminativeness and reliability, suppressing corrupted spatial regions and feature channels during cross-scale fusion. Experimental results on real-world datasets from diverse domains, including BreakHis at 40×, 100×, 200×, and 400× magnifications, Oxford-IIIT Pet, and Chest X-ray, demonstrate the superiority of the proposed method over baseline models in classification accuracy, convergence stability, and robustness to cross-scale Gaussian noise.
SN - 2227-7390
ER -