mlsanityData to 7 Oct 2026

Generative Active Learning for Long-tailed Instance Segmentation

arXiv 2406.02435 ↗First posted 4 Jun 2024cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Recently, large-scale language-image generative models have gained widespread attention and many works have utilized generated data from these models to further enhance the performance of perception tasks. However, not all generated data can positively impact downstream models, and these methods do not thoroughly explore how to better select and utilize generated data. On the other hand, there is still a lack of research oriented towards active learning on generated data. In this paper, we explore how to perform active learning specifically for generated data in the long-tailed instance segmentation task. Subsequently, we propose BSGAL, a new algorithm that online estimates the contribution of the generated data based on gradient cache. BSGAL can handle unlimited generated data and complex downstream segmentation tasks effectively. Experiments show that BSGAL outperforms the baseline approach and effectually improves the performance of long-tailed segmentation. Our code can be found at https://github.com/aim-uofa/DiverGen.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 46 of its 66 references that are in the map. First posted on arXiv 4 Jun 2024.

Builds on

46 of 66 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2023Segment Anythingcited by 8,158
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  6. 2022Generative Adversarial Networkscited by 5,603
  7. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  8. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  9. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  10. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  11. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 577
  12. 2020Estimating Training Data Influence by Tracing Gradient Descentcited by 565
34 more
  1. 2020A Survey of Deep Active Learningcited by 547
  2. 2021Image Segmentation Using Text and Image Promptscited by 509
  3. 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 492
  4. 2020U2-Net: Going Deeper with Nested U-Structure for Salient Object Detectioncited by 410
  5. 2023Synthetic Data from Diffusion Models Improves ImageNet Classificationcited by 326
  6. 2021DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effortcited by 264
  7. 2023Key-Locked Rank One Editing for Text-to-Image Personalizationcited by 194
  8. 2018Representer Point Selection for Explaining Deep Neural Networkscited by 187
  9. 2023Semantic-SAM: Segment and Recognize Anything at Any Granularitycited by 185
  10. 2023DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Modelscited by 162
  11. 2023Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learnerscited by 152
  12. 2023Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuningcited by 150
  13. 2023Matcher: Segment Anything with One Shot Using All-Purpose Feature Matchingcited by 142
  14. 2022Training Data Influence Analysis and Estimation: A Surveycited by 134
  15. 2021Probabilistic two-stage detectioncited by 130
  16. 2023DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Modelscited by 122
  17. 2023Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applicationscited by 121
  18. 2022BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotationscited by 99
  19. 2021Gone Fishing: Neural Active Learning with Fisher Embeddingscited by 88
  20. 2017Deep Active Learning over the Long Tailcited by 82
  21. 2021Influence Selection for Active Learningcited by 82
  22. 2023Open-vocabulary Object Segmentation with Diffusion Modelscited by 82
  23. 2018Efficient Active Learning for Image Classification and Segmentation using a Sample Selection and Conditional Generative Adversarial Networkcited by 74
  24. 2023Sensitivity-Aware Visual Parameter-Efficient Fine-Tuningcited by 74
  25. 2024Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactivelycited by 74
  26. 2023FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Modelscited by 61
  27. 2020Reinforced active learning for image segmentationcited by 56
  28. 2022X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusioncited by 49
  29. 2022Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinitycited by 41
  30. 2023MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentationcited by 35
  31. 2022SelfReformer: Self-Refined Network with Transformer for Salient Object Detectioncited by 20
  32. 2023Streaming Active Learning with Deep Neural Networkscited by 20
  33. 2023SegPrompt: Boosting Open-world Segmentation via Category-level Prompt Learningcited by 17
  34. 2024DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Datacited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 5; 2026: 2.

10 papers.

  1. 2025Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaborationcited by 38
  2. 2025SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectoriescited by 29
  3. 2024A Systematic Review on Long-Tailed Learningcited by 27
  4. 2024A Simple Image Segmentation Framework via In-Context Examplescited by 19
  5. 2024Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentationcited by 16
  6. 2025Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Datacited by 15
  7. 2025Rethinking Long-tailed Dataset Distillation: A Uni-Level Framework with Unbiased Recovery and Relabelingcited by 3
  8. 2025Active Learning Inspired ControlNet Guidance for Augmenting Semantic Segmentation Datasetscited by 2
  9. 2026Optimized Deferral for Imbalanced Settingscited by 2
  10. 2026Greedy Volume Maximization of Gradient Embeddings for Long-Tailed Frame-Level Bioacoustic Active Learningcited by 0