mlsanityData to 14 Oct 2026

LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content

arXiv 2403.05854 ↗First posted 9 Mar 2024cs.CVcited by 33

Not on the map. Why?

Abstract (arXiv)

Long-tail recognition is challenging because it requires the model to learn good representations from tail categories and address imbalances across all categories. In this paper, we propose a novel generative and fine-tuning framework, LTGC, to handle long-tail recognition via leveraging generated content. Firstly, inspired by the rich implicit knowledge in large-scale models (e.g., large language models, LLMs), LTGC leverages the power of these models to parse and reason over the original tail data to produce diverse tail-class content. We then propose several novel designs for LTGC to ensure the quality of the generated data and to efficiently fine-tune the model using both the generated and original data. The visualization demonstrates the effectiveness of the generation module in LTGC, which produces accurate and diverse tail data. Additionally, the experimental results demonstrate that our LTGC outperforms existing state-of-the-art methods on popular long-tailed benchmarks.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). Builds on 51 of its 65 references that are in the map. First posted on arXiv 9 Mar 2024.

Builds on

51 of 65 references.

References · 51

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  6. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  7. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  8. 2019Invariant Risk Minimizationcited by 1,854
  9. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  10. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  11. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  12. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
38 more
  1. 2023The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)cited by 681
  2. 2023Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generatorscited by 670
  3. 2023MiniGPT-v2: large language model as a unified interface for vision-language multi-task learningcited by 625
  4. 2020Long-tail learning via logit adjustmentcited by 618
  5. 2022ProgPrompt: Generating Situated Robot Task Plans using Large Language Modelscited by 611
  6. 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 513
  7. 2021Deep Long-Tailed Learning: A Surveycited by 417
  8. 2023Effective Data Augmentation With Diffusion Modelscited by 283
  9. 2020Long-tailed Recognition by Routing Diverse Distribution-Aware Expertscited by 271
  10. 2023RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulationcited by 218
  11. 2021Parametric Contrastive Learningcited by 217
  12. 2020Rethinking the Value of Labels for Improving Class-Imbalanced Learningcited by 216
  13. 2021Improving Calibration for Long-Tailed Recognitioncited by 212
  14. 2020Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classificationcited by 175
  15. 2020Disentangling Label Distribution for Long-tailed Visual Recognitioncited by 172
  16. 2015Cost Sensitive Learning of Deep Feature Representations from Imbalanced Datacited by 167
  17. 2020Remix: Rebalanced Mixupcited by 144
  18. 2022Balanced Contrastive Learning for Long-Tailed Visual Recognitioncited by 144
  19. 2021Targeted Supervised Contrastive Learning for Long-Tailed Recognitioncited by 132
  20. 2023Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challengescited by 131
  21. 2021Contrastive Learning based Hybrid Networks for Long-Tailed Image Classificationcited by 130
  22. 2022Retrieval Augmented Classification for Long-Tail Visual Recognitioncited by 106
  23. 2023Contextual Object Detection with Multimodal Large Language Modelscited by 100
  24. 2021MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognitioncited by 99
  25. 2022LPT: Long-tailed Prompt Tuning for Image Classificationcited by 69
  26. 2021VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognitioncited by 65
  27. 2022Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learningcited by 57
  28. 2023Towards Language Models That Can See: Computer Vision Through the LENS of Natural Languagecited by 53
  29. 2018Counterfactuals uncover the modular structure of deep generative modelscited by 51
  30. 2023LLaFS: When Large Language Models Meet Few-Shot Segmentationcited by 48
  31. 2021Self-Supervised Learning Disentangled Group Representation as Featurecited by 47
  32. 2022Invariant Feature Learning for Generalized Long-Tailed Classificationcited by 34
  33. 2017The iNaturalist Species Classification and Detection Datasetcited by 29
  34. 2023AI-Generated Content (AIGC) for Various Data Modalities: A Surveycited by 25
  35. 2021Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classificationcited by 24
  36. 2022Balanced Product of Calibrated Experts for Long-Tailed Recognitioncited by 20
  37. 2023MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognitioncited by 19
  38. 2023MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformercited by 15

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 10; 2025: 12; 2026: 11.

33 papers.

Sort:

By area:

  1. 2024A Survey on Data Synthesis and Augmentation for Large Language Modelscited by 41
  2. 2024MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmarkcited by 41
  3. 2024A Systematic Review on Long-Tailed Learningcited by 28
  4. 2024Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generationcited by 25
  5. 2024Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackerscited by 24
  6. 2024A Survey on Recent Advances in Conversational Data Generationcited by 23
  7. 2024Preference-Guided Refactored Tuning for Retrieval Augmented Code Generationcited by 10
  8. 2025From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibrationcited by 8
  9. 2024Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Datacited by 7
  10. 2024LTRL: Boosting Long-tail Recognition via Reflective Learningcited by 6
  11. 2025AIM-Fair: Advancing Algorithmic Fairness via Selectively Fine-Tuning Biased Models with Contextual Synthetic Datacited by 5
  12. 2025Free-Grained Hierarchical Visual Recognitioncited by 3
21 more
  1. 2025Rethinking Long-tailed Dataset Distillation: A Uni-Level Framework with Unbiased Recovery and Relabelingcited by 3
  2. 2025Open Ad-hoc Categorization with Contextualized Feature Learningcited by 3
  3. 2025LLM-empowered Dynamic Prompt Routing for Vision-Language Models Tuning under Long-Tailed Distributionscited by 2
  4. 2026On the Difficulty of Learning a Meta-network for Training Data Selectioncited by 2
  5. 2025Divide, Weight, and Route: Difficulty-Aware Optimization with Dynamic Expert Fusion for Long-tailed Recognitioncited by 1
  6. 2025Training-Free Label Space Alignment for Universal Domain Adaptationcited by 1
  7. 2025Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learningcited by 1
  8. 2026Reframing Long-Tailed Learning via Loss Landscape Geometrycited by 1
  9. 2026Self-Reinforcing Controllable Synthesis of Rare Relational Data via Bayesian Calibrationcited by 1
  10. 2024SAU: A Dual-Branch Network to Enhance Long-Tailed Recognition via Generative Modelscited by 0
  11. 2025ULFine: Unbiased Lightweight Fine-tuning for Foundation-Model-Assisted Long-Tailed Semi-Supervised Learningcited by 0
  12. 2025Semantic-guided Fine-tuning of Foundation Model for Long-tailed Visual Recognitioncited by 0
  13. 2025Salient Concept-Aware Generative Data Augmentationcited by 0
  14. 2026Beyond the Majority: Long-tail Imitation Learning for Robotic Manipulationcited by 0
  15. 2026Compensating Visual Insufficiency with Stratified Language Guidance for Long-Tail Class Incremental Learningcited by 0
  16. 2026SciLT: Long-tailed Image Classification under Scientific Image Domainscited by 0
  17. 2026ARGen: Affect-Reinforced Generative Augmentation towards Vision-based Dynamic Emotion Perceptioncited by 0
  18. 2026Manifold-Constrained Adversarial Training for Long-Tailed Robustness via Geometric Alignmentcited by 0
  19. 2026Toward Multi-Domain and Long-Tailed Quantization via Feature Alignment and Scalingcited by 0
  20. 2026Gen2Balance: Generative Balancing for Long-Tailed Video Action Recognitioncited by 0
  21. 2026OFBD: Object-Focused Background Debiasing for Long-Tailed Learningcited by 0