eess.IVNov 19, 2026

Breaking Noise Shortcuts in Self-Supervised Learning Via Noise-Aligned View Generation

Authors: Oankar R. Patil, May D. Wang

Organizations: Department of Electrical & Computer Engineering, Georgia Institute of Technology, Atlanta, GA, 30332 · Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GA, 30332

Abstract

Self-supervised learning (SSL) is increasingly applied to scientific imaging domains, such as microscopy, where labels are scarce but noisy data is abundant. These domains exhibit significant signal-dependent noise, which can create a representational shortcut: since both augmented views derive from the same noisy image, the encoder can boost view agreement by also encoding noise patterns rather than semantic content. To enable noise-robust representation learning without knowledge of underlying noise models, we introduce Self-Aligned Noise Augmentation (SEANA), a drop-in module that generates noise-aware SSL views. SEANA learns an invertible variance-stabilizing transform (VST) from noisy data, then estimates the clean signal and resamples independent noise in learned VST space, requiring no clean targets, no dataset-specific denoiser training or use at inference, and no changes to the SSL objective or encoder. On CIFAR-10 and ImageNet-100 under synthetic Gaussian, Poisson-Gaussian, and multiplicative noise, SEANA improves clean-test linear-probe accuracy across contrastive/non-contrastive SSL methods, indicating higher-quality representations. On real fluorescence imaging, SEANA improves Jurkat cell-cycle stage classification by up to 28.6pp over standard SSL and 27.5pp over denoiser-preprocessed baselines. In all settings, SEANA outperforms the denoiser-preprocessed SSL pipelines, demonstrating that learned VST-space noise-aligned resampling yields more robust representations than denoising alone. Code is available at: https://github.com/opatil31/SEANA

Figures & tables

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Physics-Aligned Self-Supervised Learning for Scientific Imaging

    Jul 30, 2026Bashir Kazimi, Stefan SandfeldElectron MicroscopyData Augmentation

  2. Trust-SSL: Additive-Residual Selective Invariance for Robust Aerial Self-Supervised Learning

    Apr 23, 2026Wadii Boulila, Adel Ammar, Bilel Benjdira +1Contrastive LearningImage Corruption Robustness

  3. Pre-train to Gain: Robust Learning Without Clean Labels

    Nov 25, 2025David Szczecina, Nicholas Pellegrino, Paul FieguthSelf-Supervised Pre-TrainingLearning with Noisy Labels