mlsanityData to 14 Oct 2026

Variational Positive-incentive Noise: How Noise Benefits Models

arXiv 2306.07651 ↗First posted 13 Jun 2023cs.LG cs.CVcited by 38

Not on the map. Why?

Abstract (arXiv)

A large number of works aim to alleviate the impact of noise due to an underlying conventional assumption of the negative role of noise. However, some existing works show that the assumption does not always hold. In this paper, we investigate how to benefit the classical models by random noise under the framework of Positive-incentive Noise (Pi-Noise). Since the ideal objective of Pi-Noise is intractable, we propose to optimize its variational bound instead, namely variational Pi-Noise (VPN). With the variational inference, a VPN generator implemented by neural networks is designed for enhancing base models and simplifying the inference of base models, without changing the architecture of base models. Benefiting from the independent design of base models and VPN generators, the VPN generator can work with most existing models. From the experiments, it is shown that the proposed VPN generator can improve the base models. It is appealing that the trained variational VPN generator prefers to blur the irrelevant ingredients in complicated images, which meets our expectations.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Builds on 17 of its 36 references that are in the map. First posted on arXiv 13 Jun 2023.

Builds on

17 of 36 references.

References · 17

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  7. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  8. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  9. 2013Intriguing properties of neural networkscited by 5,155
  10. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  11. 2019When Does Label Smoothing Help?cited by 988
  12. 2016Deep Variational Information Bottleneckcited by 930
5 more
  1. 2017One pixel attack for fooling deep neural networkscited by 582
  2. 2020Graph Information Bottleneckcited by 168
  3. 2017Learning Discrete Representations via Information Maximizing Self-Augmented Trainingcited by 149
  4. 2015Distributional Smoothing with Virtual Adversarial Trainingcited by 61
  5. 2022Positive-incentive Noisecited by 39

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 4; 2025: 20; 2026: 12.

38 papers.

Sort:

By area:

  1. 2024Enhance Vision-Language Alignment with Noisecited by 34
  2. 2024Data Augmentation of Contrastive Learning is Estimating Positive-incentive Noisecited by 25
  3. 2025Learn Beneficial Noise as Graph Augmentationcited by 15
  4. 2025NFIG: Multi-Scale Autoregressive Image Generation via Frequency Orderingcited by 14
  5. 2025Adv-CPG: A Customized Portrait Generation Framework with Facial Adversarial Attackscited by 14
  6. 2025Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learningcited by 14
  7. 2025Object-AVEdit: An Object-level Audio-Visual Editing Modelcited by 14
  8. 2025Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advancescited by 12
  9. 2025Explore How to Inject Beneficial Noise in MLLMscited by 10
  10. 2025MR-UIE: Multi-Perspective Reasoning with Reinforcement Learning for Universal Information Extractioncited by 6
  11. 2025Laytrol: Preserving Pretrained Knowledge in Layout Control for Multimodal Diffusion Transformerscited by 6
  12. 2026Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generationcited by 6
26 more
  1. 2023NoisyNN: Exploring the Impact of Information Entropy Change in Learning Systemscited by 5
  2. 2026InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatarscited by 5
  3. 2024CNN2GNN: How to Bridge CNN with GNNcited by 3
  4. 2025AnchorFormer: Differentiable Anchor Attention for Efficient Vision Transformercited by 3
  5. 2025TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answeringcited by 3
  6. 2026Enhancing Neural Video Compression of Static Scenes with Positive-Incentive Noisecited by 3
  7. 2024SRAGAN: Saliency Regularized and Attended Generative Adversarial Network for Chinese Ink-wash Painting Style Transfercited by 2
  8. 2025GRPO-RM: Fine-Tuning Representation Models via GRPO-Driven Reinforcement Learningcited by 2
  9. 2026Perturbation-Regularized Open-Vocabulary Remote Sensing Segmentation with Unified Multi-Domain Evaluationcited by 2
  10. 2023Data-Centric Long-Tailed Image Recognitioncited by 1
  11. 2025Unveiling Hidden Vulnerabilities in Digital Human Generation via Adversarial Attackscited by 1
  12. 2025ERF-BA-TFD+: A Multimodal Model for Audio-Visual Deepfake Detectioncited by 1
  13. 2025ViewMask-1-to-3: Multi-View Consistent Image Generation via Multimodal Discrete Diffusion Modelscited by 1
  14. 2026Safeguarding Text-to-Image Generative Models Against Unauthorized Knowledge Distillationcited by 1
  15. 2026Semantic-Aware Temporal Adaptation for UAV Anti-UAV Trackingcited by 1
  16. 2025Exploiting the Potential Supervision Information of Clean Samples in Partial Label Learningcited by 0
  17. 2025Real-Time Crowd Counting for Embedded Systems with Lightweight Architecturecited by 0
  18. 2025CoLM: Collaborative Large Models via A Client-Server Paradigmcited by 0
  19. 2025How Noise Benefits AI-generated Image Detectioncited by 0
  20. 2025Multi-Intent Spoken Language Understanding: Methods, Trends, and Challengescited by 0
  21. 2026Noise-Robust Tiny Object Localization with Flowscited by 0
  22. 2026Batch Loss Score for Dynamic Data Pruningcited by 0
  23. 2026Latent Noise Mask for Reducing Visual Redundancy in Multimodal Large Language Modelscited by 0
  24. 2026Representation Learning in Diffusion and Flow-based Model: An Application Aspectcited by 0
  25. 2026On-Policy Distillation for Vision-Language Model Adaptation, an Effective Paradigm on Low-Quality Multimodal Datacited by 0
  26. 2026Incentive Noise and Structural Prior Infusion for Multi-modal Object Re-Identificationcited by 0