Interleaved Noise Injection Improves Clean, Corrupted, and OOD Performance

• URL: http://arxiv.org/abs/2607.14466v1
• Date: Thu, 16 Jul 2026 01:25:44 GMT
• Title: Interleaved Noise Injection Improves Clean, Corrupted, and OOD Performance
• Abstract summary: We present a theoretical analysis of noise injection, which confirms that corruption by impulse noise approximates a Jacobian regularization.<n>We show that the effect of interleaved noise injection stems from penalizing the failure modes encouraged by the inductive bias of the models.<n>Interleaved noise injection is therefore an effective tool to improve the test performance on clean, noisy, and out-of-distribution data at essentially zero computational cost.
• Score: 1.6567880228735357
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Noise injection is a well-known technique in stochastic optimization. We report its surprising effectiveness with an interleaved (on-off-on-off...) rather than the usual monotonic decay schedule. We present a theoretical analysis of noise injection, which confirms that corruption by impulse noise approximates a Jacobian regularization, whereas Gaussian noise acts as a curvature penalty. This regularization behavior has been invoked to explain why noise injection increases model robustness. But the interleaved nature of our proposed schedule produces superior results even for the optimization objective: mixing phases of noisy data permits the optimizer to escape local minima and increase exploration without the risk of catastrophically forgetting the important features from the clean data. To stabilize this training scheme against the rapid changes of the loss when switching between clean and noisy data, we introduce a gradient-norm stabilization technique that scales noisy updates based on clean gradient magnitudes. We compare this method with other common augmentation methods and find substantial improvements in corruption tolerance and robustness to real-world distribution shifts on CIFAR-100-C, ImageNet-C, and ImageNet-R for ResNet and ViT architectures, with the best results being achieved by stacking our method on top of other augmentations. Through saliency and attention maps we show that the effect of interleaved noise injection stems from penalizing the failure modes encouraged by the inductive bias of the models: impulse noise works against the locality bias of convolutional (ResNet) architectures, and Gaussian noise reduces the tendency of attention-based models to pick up large-scale spurious features. Interleaved noise injection is therefore an effective tool to improve the test performance on clean, noisy, and out-of-distribution data at essentially zero computational cost.

Related papers

• NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training [81.58321000203712]
  NoiseRater is a meta-learning framework for instance-level noise valuation in diffusion model training.<n>NoiseRater assigns importance scores to individual noise realizations conditioned on data and timestep.<n>Experiments on FFHQ and ImageNet demonstrate that not all noise samples contribute equally.
  arXiv  Detail & Related papers  (2026-05-02T19:43:16Z)
• NADD: Amplifying Noise for Effective Diffusion-based Adversarial Purification [15.051303733999392]
  A strategy of combining diffusion-based generative models with classifiers continues to demonstrate state-of-the-art performance on adversarial robustness benchmarks.<n>Known as adversarial purification, this exploits a diffusion model's capability of identifying high density regions in data distributions to purify adversarial perturbations from inputs.<n>Existing diffusion-based purification defenses are impractically slow and limited in robustness due to the low levels of noise used in the diffusion process.<n>We propose a new sampling method which introduces additional noise during the reverse diffusion process to dilute adversarial perturbations.
  arXiv  Detail & Related papers  (2026-01-03T08:10:43Z)
• Noise-Robust Tiny Object Localization with Flows [63.60972031108944]
  We propose a noise-robust localization framework leveraging normalizing flows for flexible error modeling and uncertainty-guided optimization.<n>Our method captures complex, non-Gaussian prediction distributions through flow-based error modeling, enabling robust learning under noisy supervision.<n>An uncertainty-aware gradient modulation mechanism further suppresses learning from high-uncertainty, noise-prone samples, mitigating overfitting while stabilizing training.
  arXiv  Detail & Related papers  (2026-01-02T09:16:55Z)
• Integrating Reweighted Least Squares with Plug-and-Play Diffusion Priors for Noisy Image Restoration [6.402777145722335]
  We propose a plug-and-play image restoration framework based on generative diffusion priors for robust removal of general noise types, including impulse noise.<n> Experimental results on benchmark datasets demonstrate that the proposed method effectively removes non-Gaussian impulse noise and achieves superior restoration performance.
  arXiv  Detail & Related papers  (2025-11-10T08:11:20Z)
• Mitigating the Noise Shift for Denoising Generative Models via Noise Awareness Guidance [54.88271057438763]
  Noise Awareness Guidance (NAG) is a correction method that explicitly steers sampling trajectories to remain consistent with the pre-defined noise schedule.<n>NAG consistently mitigates noise shift and substantially improves the generation quality of mainstream diffusion models.
  arXiv  Detail & Related papers  (2025-10-14T13:31:34Z)
• A self-supervised learning approach for denoising autoregressive models with additive noise: finite and infinite variance cases [0.9217021281095907]
  In applications, autoregressive signals are often corrupted by additive noise.<n>In this paper, we propose a novel self-supervised learning method to denoise the additive noise-corrupted autoregressive model.
  arXiv  Detail & Related papers  (2025-08-18T14:46:56Z)
• Machine Unlearning for Robust DNNs: Attribution-Guided Partitioning and Neuron Pruning in Noisy Environments [5.8166742412657895]
  Deep neural networks (DNNs) have achieved remarkable success across diverse domains, but their performance can be severely degraded by noisy or corrupted training data.<n>We propose a novel framework that integrates attribution-guided data partitioning, discriminative neuron pruning, and targeted fine-tuning to mitigate the impact of noisy samples.<n>Our framework achieves approximately a 10% absolute accuracy improvement over standard retraining on CIFAR-10 with injected label noise.
  arXiv  Detail & Related papers  (2025-06-13T09:37:11Z)
• Divide and Conquer: Heterogeneous Noise Integration for Diffusion-based Adversarial Purification [75.09791002021947]
  Existing purification methods aim to disrupt adversarial perturbations by introducing a certain amount of noise through a forward diffusion process, followed by a reverse process to recover clean examples.<n>This approach is fundamentally flawed as the uniform operation of the forward process compromises normal pixels while attempting to combat adversarial perturbations.<n>We propose a heterogeneous purification strategy grounded in the interpretability of neural networks.<n>Our method decisively applies higher-intensity noise to specific pixels that the target model focuses on while the remaining pixels are subjected to only low-intensity noise.
  arXiv  Detail & Related papers  (2025-03-03T11:00:25Z)
• Negative Pre-aware for Noisy Cross-modal Matching [46.5591267410225]
  Cross-modal noise-robust learning is a challenging task since noisy correspondence is hard to recognize and rectify. We present a novel Negative Pre-aware Cross-modal matching solution for large visual-language model fine-tuning on noisy downstream tasks.
  arXiv  Detail & Related papers  (2023-12-10T05:52:36Z)
• DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection [80.20339155618612]
  DiffusionAD is a novel anomaly detection pipeline comprising a reconstruction sub-network and a segmentation sub-network.<n>A rapid one-step denoising paradigm achieves hundreds of times acceleration while preserving comparable reconstruction quality.<n>Considering the diversity in the manifestation of anomalies, we propose a norm-guided paradigm to integrate the benefits of multiple noise scales.
  arXiv  Detail & Related papers  (2023-03-15T16:14:06Z)
• SAR Despeckling using a Denoising Diffusion Probabilistic Model [52.25981472415249]
  The presence of speckle degrades the image quality and adversely affects the performance of SAR image understanding applications. We introduce SAR-DDPM, a denoising diffusion probabilistic model for SAR despeckling. The proposed method achieves significant improvements in both quantitative and qualitative results over the state-of-the-art despeckling methods.
  arXiv  Detail & Related papers  (2022-06-09T14:00:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.