mlsanityData to 14 Oct 2026

VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition

arXiv 2111.13579 ↗First posted 26 Nov 2021cs.CVcited by 65

Not on the map. Why?

Abstract (arXiv)

Deep learning-based models encounter challenges when processing long-tailed data in the real world. Existing solutions usually employ some balancing strategies or transfer learning to deal with the class imbalance problem, based on the image modality. In this work, we present a visual-linguistic long-tailed recognition framework, termed VL-LTR, and conduct empirical studies on the benefits of introducing text modality for long-tailed recognition (LTR). Compared to existing approaches, the proposed VL-LTR has the following merits. (1) Our method can not only learn visual representation from images but also learn corresponding linguistic representation from noisy class-level text descriptions collected from the Internet; (2) Our method can effectively use the learned visual-linguistic representation to improve the visual recognition performance, especially for classes with fewer image samples. We also conduct extensive experiments and set the new state-of-the-art performance on widely-used LTR benchmarks. Notably, our method achieves 77.2% overall accuracy on ImageNet-LT, which significantly outperforms the previous best method by over 17 points, and is close to the prevailing performance training on the full ImageNet. Code is available at https://github.com/ChangyaoTian/VL-LTR.

Key facts. Cited by 65 papers in the map (data through 14 Oct 2026). Builds on 38 of its 59 references that are in the map. First posted on arXiv 26 Nov 2021.

Builds on

38 of 59 references.

References · 38

  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. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  5. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  6. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  7. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  8. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  9. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,222
  10. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,553
  11. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  12. 2020Oscar: Object-Semantics Aligned Pre-training for Vision-Language Taskscited by 1,214
26 more
  1. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  2. 2019VL-BERT: Pre-training of Generic Visual-Linguistic Representationscited by 954
  3. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  4. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
  5. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 605
  6. 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 513
  7. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  8. 2020HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-trainingcited by 362
  9. 2020Large-Scale Adversarial Training for Vision-and-Language Representation Learningcited by 327
  10. 2020Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformerscited by 288
  11. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  12. 201912-in-1: Multi-Task Vision and Language Representation Learningcited by 278
  13. 2020Long-tailed Recognition by Routing Diverse Distribution-Aware Expertscited by 271
  14. 2019UNITER: UNiversal Image-TExt Representation Learningcited by 228
  15. 2021Parametric Contrastive Learningcited by 217
  16. 2015Cost Sensitive Learning of Deep Feature Representations from Imbalanced Datacited by 167
  17. 2020Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspectivecited by 143
  18. 2020Feature Space Augmentation for Long-Tailed Datacited by 136
  19. 2020M2m: Imbalanced Classification via Major-to-minor Translationcited by 134
  20. 2021Contrastive Learning based Hybrid Networks for Long-Tailed Image Classificationcited by 130
  21. 2021ResLT: Residual Learning for Long-tailed Recognitioncited by 96
  22. 2021Distributional Robustness Loss for Long-tail Learningcited by 84
  23. 2021Self Supervision to Distillation for Long-Tailed Visual Recognitioncited by 73
  24. 2017Fine-graind Image Classification via Combining Vision and Languagecited by 51
  25. 2020A Closer Look at the Robustness of Vision-and-Language Pre-trained Modelscited by 37
  26. 2019Shaping Visual Representations with Language for Few-shot Classificationcited by 27

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 8; 2023: 19; 2024: 18; 2025: 15; 2026: 5.

65 papers.

Sort:

By area:

  1. 2022Vision-Language Pre-training: Basics, Recent Advances, and Future Trendscited by 117
  2. 2022K-LITE: Learning Transferable Visual Models with External Knowledgecited by 79
  3. 2023Generating images of rare concepts using pre-trained diffusion modelscited by 79
  4. 2022LPT: Long-tailed Prompt Tuning for Image Classificationcited by 69
  5. 2022Expanding Small-Scale Datasets with Guided Imaginationcited by 62
  6. 2023Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurtscited by 58
  7. 2024Improved Zero-Shot Classification by Adapting VLMs with Text Descriptionscited by 54
  8. 2023Norm-guided latent space exploration for text-to-image generationcited by 43
  9. 2024Probabilistic Contrastive Learning for Long-Tailed Visual Recognitioncited by 42
  10. 2024In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentationcited by 38
  11. 2023Exploring Vision-Language Models for Imbalanced Learningcited by 35
  12. 2023Fill-Up: Balancing Long-Tailed Data with Generative Modelscited by 34
38 more
  1. 2023Distilling Large Vision-Language Model with Out-of-Distribution Generalizabilitycited by 33
  2. 2023Feedback-guided Data Synthesis for Imbalanced Classificationcited by 33
  3. 2024LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Contentcited by 33
  4. 2022Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Informationcited by 31
  5. 2024A Systematic Review on Long-Tailed Learningcited by 28
  6. 2023Improving Image Recognition by Retrieving from Web-Scale Image-Text Datacited by 20
  7. 2024Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwardscited by 19
  8. 2023Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labelscited by 16
  9. 2023LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognitioncited by 15
  10. 2024Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognitioncited by 15
  11. 2024DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasetscited by 14
  12. 2022Cap2Aug: Caption guided Image to Image data Augmentationcited by 10
  13. 2023TextManiA: Enriching Visual Feature by Text-driven Manifold Augmentationcited by 9
  14. 2024Learning from Neighbors: Category Extrapolation for Long-Tail Learningcited by 9
  15. 2023GeNIe: Generative Hard Negative Images Through Diffusioncited by 8
  16. 2023Exploring Weight Balancing on Long-Tailed Recognition Problemcited by 7
  17. 2023SCoRe: Submodular Combinatorial Representation Learningcited by 7
  18. 2024VLM-KD: Knowledge Distillation from VLM for Long-Tail Visual Recognitioncited by 7
  19. 2023Factorization Vision Transformer: Modeling Long Range Dependency with Local Window Costcited by 5
  20. 2024Category-Prompt Refined Feature Learning for Long-Tailed Multi-Label Image Classificationcited by 5
  21. 2025LIFT+: Lightweight Fine-Tuning for Long-Tail Learningcited by 5
  22. 2025Equipping Vision Foundation Model with Mixture of Experts for Out-of-Distribution Detectioncited by 5
  23. 2024VLMine: Long-Tail Data Mining with Vision Language Modelscited by 4
  24. 2022VLG: General Video Recognition with Web Textual Knowledgecited by 3
  25. 2023DiffDis: Empowering Generative Diffusion Model with Cross-Modal Discrimination Capabilitycited by 3
  26. 2023Uniformly Distributed Category Prototype-Guided Vision-Language Framework for Long-Tail Recognitioncited by 3
  27. 2025Free-Grained Hierarchical Visual Recognitioncited by 3
  28. 2023Set Learning for Accurate and Calibrated Modelscited by 2
  29. 2025Generate, Transduct, Adapt: Iterative Transduction with VLMscited by 2
  30. 2025Empowering Vision Transformers with Multi-Scale Causal Intervention for Long-Tailed Image Classificationcited by 2
  31. 2025LLM-empowered Dynamic Prompt Routing for Vision-Language Models Tuning under Long-Tailed Distributionscited by 2
  32. 2025Dual-View Alignment Learning with Hierarchical-Prompt for Class-Imbalance Multi-Label Classificationcited by 2
  33. 2024IMWA: Iterative Model Weight Averaging Benefits Class-Imbalanced Learning Taskscited by 1
  34. 2024Large Language Model Informed Patent Image Retrievalcited by 1
  35. 2024WIDIn: Wording Image for Domain-Invariant Representation in Single-Source Domain Generalizationcited by 1
  36. 2024Text-Guided Mixup Towards Long-Tailed Image Categorizationcited by 1
  37. 2024LPT++: Efficient Training on Mixture of Long-tailed Expertscited by 1
  38. 2024Multiplicative Logit Adjustment Approximates Neural-Collapse-Aware Decision Boundary Adjustmentcited by 1

50 most cited of 65 All 65 (JSON)