mlsanityData to 7 Oct 2026

DiffuLT: How to Make Diffusion Model Useful for Long-tail Recognition

arXiv 2403.05170 ↗First posted 8 Mar 2024cs.CVcited by 3

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

This paper proposes a new pipeline for long-tail (LT) recognition. Instead of re-weighting or re-sampling, we utilize the long-tailed dataset itself to generate a balanced proxy that can be optimized through cross-entropy (CE). Specifically, a randomly initialized diffusion model, trained exclusively on the long-tailed dataset, is employed to synthesize new samples for underrepresented classes. Then, we utilize the inherent information in the original dataset to filter out harmful samples and keep the useful ones. Our strategy, Diffusion model for Long-Tail recognition (DiffuLT), represents a pioneering utilization of generative models in long-tail recognition. DiffuLT achieves state-of-the-art results on CIFAR10-LT, CIFAR100-LT, and ImageNet-LT, surpassing the best competitors with non-trivial margins. Abundant ablations make our pipeline interpretable, too. The whole generation pipeline is done without any external data or pre-trained model weights, making it highly generalizable to real-world long-tailed settings.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 47 of its 53 references that are in the map. First posted on arXiv 8 Mar 2024.

Builds on

47 of 53 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023Class-Balancing Diffusion Models30 Apr
  2. 2022Few-Shot Diffusion Models30 May
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  4. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  6. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  6. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  7. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  8. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  9. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  10. 2018AutoAugment: Learning Augmentation Policies from Datacited by 728
  11. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  12. 2020Long-tail learning via logit adjustmentcited by 605
29 more
  1. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  2. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 397
  3. 2023Synthetic Data from Diffusion Models Improves ImageNet Classificationcited by 326
  4. 2020Long-tailed Recognition by Routing Diverse Distribution-Aware Expertscited by 270
  5. 2021DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effortcited by 264
  6. 2021Parametric Contrastive Learningcited by 217
  7. 2021Improving Calibration for Long-Tailed Recognitioncited by 212
  8. 2020Feature Space Augmentation for Long-Tailed Datacited by 136
  9. 2020M2m: Imbalanced Classification via Major-to-minor Translationcited by 134
  10. 2023Scaling Laws of Synthetic Images for Model Training ... for Nowcited by 107
  11. 2021The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classificationcited by 100
  12. 2021ResLT: Residual Learning for Long-tailed Recognitioncited by 96
  13. 2023Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustmentcited by 75
  14. 2021Self Supervision to Distillation for Long-Tailed Visual Recognitioncited by 73
  15. 2021Distilling Virtual Examples for Long-tailed Recognitioncited by 72
  16. 2022LPT: Long-tailed Prompt Tuning for Image Classificationcited by 69
  17. 2022Expanding Small-Scale Datasets with Guided Imaginationcited by 61
  18. 2023Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurtscited by 58
  19. 2021Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspectivecited by 39
  20. 2023How Re-sampling Helps for Long-Tail Learning?cited by 36
  21. 2021MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detectioncited by 33
  22. 2023CUDA: Curriculum of Data Augmentation for Long-Tailed Recognitioncited by 30
  23. 2022Escaping Saddle Points for Effective Generalization on Class-Imbalanced Datacited by 28
  24. 2023Subclass-balancing Contrastive Learning for Long-tailed Recognitioncited by 26
  25. 2023A Unified Perspective for Loss-Oriented Imbalanced Learning via Localizationcited by 24
  26. 2023DiffusionEngine: Diffusion Model is Scalable Data Engine for Object Detectioncited by 23
  27. 2023Multi-Label Self-Supervised Learning with Scene Imagescited by 17
  28. 2019Active Generative Adversarial Network for Image Classificationcited by 5
  29. 2024Rectify the Regression Bias in Long-Tailed Object Detectioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.

  1. 2024Robust Disaster Assessment from Aerial Imagery Using Text-to-Image Synthetic Datacited by 4
  2. 2025Language-Informed Hyperspectral Image Synthesis for Imbalanced-Small Sample Classification via Semi-Supervised Conditional Diffusion Modelcited by 1
  3. 2026Why Not Hyperparameter-Friendly Optimisation? A Monotonic Adaptive Norm Rescaling Approach For Long-Tailed Recognitioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Latent-based Diffusion Model for Long-tailed Recognition
  2. 2023DiffuGen: Adaptable Approach for Generating Labeled Image Datasets using Stable Diffusion Models
  3. 2023ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Process
  4. 2026Enhanced Low-Density Region Exploration in Classifier-Guided Diffusion Models Through Modified Reverse Diffusion Sampling
  5. 2025CORAL: Disentangling Latent Representations in Long-Tailed Diffusion
  6. 2025Efficient Long-Tail Learning in Latent Space by sampling Synthetic Data
  7. 2025Beyond Linear Diffusions: Improved Representations for Rare Conditional Generative Modeling
  8. 2025Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression