mlsanityData to 14 Oct 2026

Enhancing Features in Long-tailed Data Using Large Vision Model

arXiv 2504.10852 ↗First posted 15 Apr 2025cs.CVcited by 2

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

Abstract (arXiv)

Language-based foundation models, such as large language models (LLMs) or large vision-language models (LVLMs), have been widely studied in long-tailed recognition. However, the need for linguistic data is not applicable to all practical tasks. In this study, we aim to explore using large vision models (LVMs) or visual foundation models (VFMs) to enhance long-tailed data features without any language information. Specifically, we extract features from the LVM and fuse them with features in the baseline network's map and latent space to obtain the augmented features. Moreover, we design several prototype-based losses in the latent space to further exploit the potential of the augmented features. In the experimental section, we validate our approach on two benchmark datasets: ImageNet-LT and iNaturalist2018.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 32 of its 43 references that are in the map. First posted on arXiv 15 Apr 2025.

Builds on

32 of 43 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021A Simple Long-Tailed Recognition Baseline via Vision-Language Model29 Nov

Other references · 31

  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. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2020Supervised Contrastive Learningcited by 2,829
  6. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,216
  7. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
  8. 2021Deep Long-Tailed Learning: A Surveycited by 417
  9. 2020Long-tailed Recognition by Routing Diverse Distribution-Aware Expertscited by 271
  10. 2021Parametric Contrastive Learningcited by 217
  11. 2020Remix: Rebalanced Mixupcited by 144
  12. 2022Balanced Contrastive Learning for Long-Tailed Visual Recognitioncited by 144
19 more
  1. 2020Feature Space Augmentation for Long-Tailed Datacited by 136
  2. 2021FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentationcited by 76
  3. 2023Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustmentcited by 75
  4. 2021Self Supervision to Distillation for Long-Tailed Visual Recognitioncited by 73
  5. 2022Nested Collaborative Learning for Long-Tailed Visual Recognitioncited by 63
  6. 2023Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurtscited by 58
  7. 2020Posterior Re-calibration for Imbalanced Datasetscited by 53
  8. 2024Probabilistic Contrastive Learning for Long-Tailed Visual Recognitioncited by 42
  9. 2023Exploring Vision-Language Models for Imbalanced Learningcited by 35
  10. 2024A Systematic Review on Long-Tailed Learningcited by 28
  11. 2021Class-Balanced Distillation for Long-Tailed Visual Recognitioncited by 27
  12. 2021Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognitioncited by 27
  13. 2024Distilling Semantic Priors from SAM to Efficient Image Restoration Modelscited by 25
  14. 2021Iterative Human and Automated Identification of Wildlife Imagescited by 22
  15. 2024DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasetscited by 14
  16. 2024Latent-based Diffusion Model for Long-tailed Recognitioncited by 14
  17. 2023Learning Prototype Classifiers for Long-Tailed Recognitioncited by 6
  18. 2024Spatial Transcriptomics Analysis of Zero-shot Gene Expression Predictioncited by 6
  19. 2022Efficient Gaussian Process Model on Class-Imbalanced Datasets for Generalized Zero-Shot Learningcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Structural Energy Guidance for View-Consistent Text-to-3D Generationcited by 0
  2. 2026Repurposing RGB-based Foundation Model for Depth Estimation on Thermal Images Using Hierarchical Supervisioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration
  2. 2024Finer: Investigating and Enhancing Fine-Grained Visual Concept Recognition in Large Vision Language Models
  3. 2024Are We on the Right Way for Evaluating Large Vision-Language Models?
  4. 2025BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding
  5. 2024VLMine: Long-Tail Data Mining with Vision Language Models
  6. 2024Rethinking VLMs and LLMs for Image Classification
  7. 2026Unsupervised Long-Tailed Adaptation of Vision-Language Models
  8. 2025Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation