mlsanityData to 7 Oct 2026

SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection

arXiv 2402.17323 ↗First posted 27 Feb 2024cs.CVcited by 42

On the map: Diffusion models → Robustness, privacy and adversarial aspects

Abstract (arXiv)

In the field of class incremental learning (CIL), generative replay has become increasingly prominent as a method to mitigate the catastrophic forgetting, alongside the continuous improvements in generative models. However, its application in class incremental object detection (CIOD) has been significantly limited, primarily due to the complexities of scenes involving multiple labels. In this paper, we propose a novel approach called stable diffusion deep generative replay (SDDGR) for CIOD. Our method utilizes a diffusion-based generative model with pre-trained text-to-diffusion networks to generate realistic and diverse synthetic images. SDDGR incorporates an iterative refinement strategy to produce high-quality images encompassing old classes. Additionally, we adopt an L2 knowledge distillation technique to improve the retention of prior knowledge in synthetic images. Furthermore, our approach includes pseudo-labeling for old objects within new task images, preventing misclassification as background elements. Extensive experiments on the COCO 2017 dataset demonstrate that SDDGR significantly outperforms existing algorithms, achieving a new state-of-the-art in various CIOD scenarios. The source code will be made available to the public.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 52 of its 71 references that are in the map. First posted on arXiv 27 Feb 2024.

Builds on

52 of 71 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Class-Incremental Learning using Diffusion Model for Distillation and Replay30 Jun

Other references · 51

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  5. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  6. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  7. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  8. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  9. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  10. 2020Denoising Diffusion Implicit Modelscited by 9,655
  11. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  12. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
38 more
  1. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  2. 2020End-to-End Object Detection with Transformerscited by 7,384
  3. 2022Classifier-Free Diffusion Guidancecited by 5,717
  4. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  5. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  6. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  7. 2016Learning without Forgettingcited by 2,465
  8. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  9. 2014Conditional Generative Adversarial Netscited by 2,152
  10. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,544
  11. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,339
  12. 2017Continual Learning with Deep Generative Replaycited by 1,152
  13. 2021Grounded Language-Image Pre-trainingcited by 1,147
  14. 2018Experience Replay for Continual Learningcited by 1,074
  15. 2023GLIGEN: Open-Set Grounded Text-to-Image Generationcited by 774
  16. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 734
  17. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 695
  18. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 486
  19. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 408
  20. 2023Composer: Creative and Controllable Image Synthesis with Composable Conditionscited by 303
  21. 2019On Tiny Episodic Memories in Continual Learningcited by 299
  22. 2021Rainbow Memory: Continual Learning with a Memory of Diverse Samplescited by 273
  23. 2018Selective Experience Replay for Lifelong Learningcited by 239
  24. 2017Incremental Learning of Object Detectors without Catastrophic Forgettingcited by 208
  25. 2022Sketch-Guided Text-to-Image Diffusion Modelscited by 180
  26. 2022ReCo: Region-Controlled Text-to-Image Generationcited by 177
  27. 2020Continual Prototype Evolution: Learning Online from Non-Stationary Data Streamscited by 143
  28. 2021OW-DETR: Open-world Detection Transformercited by 129
  29. 2021On Learning the Geodesic Path for Incremental Learningcited by 85
  30. 2020GAN Memory with No Forgettingcited by 84
  31. 2023Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable Diffusioncited by 81
  32. 2022Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillationcited by 72
  33. 2021Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inferencecited by 66
  34. 2023Continual Detection Transformer for Incremental Object Detectioncited by 59
  35. 2020RODEO: Replay for Online Object Detectioncited by 35
  36. 2020SID: Incremental Learning for Anchor-Free Object Detection via Selective and Inter-Related Distillationcited by 32
  37. 2023Boosting Human-Object Interaction Detection with Text-to-Image Diffusion Modelcited by 21
  38. 2022Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learningcited by 14

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 24; 2026: 12.

42 papers.

Sort:

By area:

  1. 2024VLM-PL: Advanced Pseudo Labeling Approach for Class Incremental Object Detection via Vision-Language Modelcited by 23
  2. 2025Synthetic Data is an Elegant GIFT for Continual Vision-Language Modelscited by 21
  3. 2024Continual Learning with Diffusion-based Generative Replay for Industrial Streaming Datacited by 6
  4. 2026When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generatorscited by 6
  5. 2025RICO: Two Realistic Benchmarks and an In-Depth Analysis for Incremental Learning in Object Detectioncited by 5
  6. 2025BlurDM: A Blur Diffusion Model for Image Deblurringcited by 5
  7. 2024DODA: Adapting Object Detectors to Dynamic Agricultural Environments in Real-Time with Diffusioncited by 4
  8. 2024Future-Proofing Class-Incremental Learningcited by 4
  9. 2025KAC: Kolmogorov-Arnold Classifier for Continual Learningcited by 4
  10. 2025Enhanced Continual Learning of Vision-Language Models with Model Fusioncited by 3
  11. 2025Harmony: A Unified Framework for Modality Incremental Learningcited by 3
  12. 2025Avoid Catastrophic Forgetting with Rank-1 Fisher from Diffusion Modelscited by 3
30 more
  1. 2024IOR: Inversed Objects Replay for Incremental Object Detectioncited by 2
  2. 2025LoRA-Loop: Closing the Synthetic Replay Cycle for Continual VLM Learningcited by 2
  3. 2025Can Synthetic Images Conquer Forgetting? Beyond Unexplored Doubts in Few-Shot Class-Incremental Learningcited by 2
  4. 2025Incremental Object Detection with Prompt-based Methodscited by 2
  5. 2025YOLO-IOD: Towards Real Time Incremental Object Detectioncited by 2
  6. 2025Beyond Synthetic Replays: Turning Diffusion Features into Few-Shot Class-Incremental Learning Knowledgecited by 1
  7. 2025Self-Controlled Dynamic Expansion Model for Continual Learningcited by 1
  8. 2025DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmeticcited by 1
  9. 2026Trust Region Continual Learning as an Implicit Meta-Learnercited by 1
  10. 2026EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformercited by 1
  11. 2026STAR-IOD: Scale-decoupled Topology Alignment with Pseudo-label Refinement for Remote Sensing Incremental Object Detectioncited by 1
  12. 2026Focus, Align, and Sustain: Counteracting Gradient Dilution in Incremental Object Detectioncited by 1
  13. 2026Symbiosis-Inspired Knowledge Distillation for Incremental Object Detectioncited by 1
  14. 2026HNDiff: Haze-Noise Diffusion for Image Dehazingcited by 1
  15. 2024CASA: Class-Agnostic Shared Attributes in Vision-Language Models for Efficient Incremental Object Detectioncited by 0
  16. 2025Incrementally Learning Multiple Diverse Data Domains via Multi-Source Dynamic Expansion Modelcited by 0
  17. 2025B-RIGHT: Benchmark Re-evaluation for Integrity in Generalized Human-Object Interaction Testingcited by 0
  18. 2025Pathological Prior-Guided Multiple Instance Learning For Mitigating Catastrophic Forgetting in Breast Cancer Whole Slide Image Classificationcited by 0
  19. 2025Exploiting Stability-Plasticity Asymmetry in Pretrained Detectors for Incremental Object Detectioncited by 0
  20. 2025GradMix: Gradient-based Selective Mixup for Robust Data Augmentation in Class-Incremental Learningcited by 0
  21. 2025Hierarchical Neural Collapse Detection Transformer for Class Incremental Object Detectioncited by 0
  22. 2025Index-Aligned Query Distillation for Transformer-based Incremental Object Detectioncited by 0
  23. 2025Parameterized Prompt for Incremental Object Detectioncited by 0
  24. 2025When Generative Replay Meets Evolving Deepfakes: Dual Confusion-Aware Regularization for Incremental Face Forgery Detectioncited by 0
  25. 2025Breaking Forgetting: Training-Free Few-Shot Class-Incremental Learning via Conditional Diffusioncited by 0
  26. 2026Continual Learning for non-stationary regression via Memory-Efficient Replaycited by 0
  27. 2026Temporal Memory for Resource-Constrained Agents: Continual Learning via Stochastic Compress-Add-Smoothcited by 0
  28. 2026Continual Learning for fMRI-Based Brain Disorder Diagnosis via Functional Connectivity Matrices Generative Replaycited by 0
  29. 2026C2Path: Class-Conditional Pathway Decoupling for Vision-Language Incremental Object Detectioncited by 0
  30. 2026DR.WILSS: Diffusion-Based Replay for Weakly Supervised Continual Semantic Segmentationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023DiffusePast: Diffusion-based Generative Replay for Class Incremental Semantic Segmentation
  2. 2023Class-Prototype Conditional Diffusion Model with Gradient Projection for Continual Learning
  3. 2024InstaGen: Enhancing Object Detection by Training on Synthetic Dataset
  4. 2023Prompt-Based Exemplar Super-Compression and Regeneration for Class-Incremental Learning
  5. 2025Diffusion Domain Teacher: Diffusion Guided Domain Adaptive Object Detector
  6. 2024Comprehensive Generative Replay for Task-Incremental Segmentation with Concurrent Appearance and Semantic Forgetting
  7. 2026Prototype Latent World Model Replay for Class-Incremental Learning
  8. 2023Continual Learning of Diffusion Models with Generative Distillation