mlsanityData to 14 Oct 2026

GistNet: a Geometric Structure Transfer Network for Long-Tailed Recognition

arXiv 2105.00131 ↗First posted 1 May 2021cs.CVcited by 31

Not on the map. Why?

Abstract (arXiv)

The problem of long-tailed recognition, where the number of examples per class is highly unbalanced, is considered. It is hypothesized that the well known tendency of standard classifier training to overfit to popular classes can be exploited for effective transfer learning. Rather than eliminating this overfitting, e.g. by adopting popular class-balanced sampling methods, the learning algorithm should instead leverage this overfitting to transfer geometric information from popular to low-shot classes. A new classifier architecture, GistNet, is proposed to support this goal, using constellations of classifier parameters to encode the class geometry. A new learning algorithm is then proposed for GeometrIc Structure Transfer (GIST), with resort to a combination of loss functions that combine class-balanced and random sampling to guarantee that, while overfitting to the popular classes is restricted to geometric parameters, it is leveraged to transfer class geometry from popular to few-shot classes. This enables better generalization for few-shot classes without the need for the manual specification of class weights, or even the explicit grouping of classes into different types. Experiments on two popular long-tailed recognition datasets show that GistNet outperforms existing solutions to this problem.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Builds on 21 of its 30 references that are in the map. First posted on arXiv 1 May 2021.

Builds on

21 of 30 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  4. 2016Matching Networks for One Shot Learningcited by 2,255
  5. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  6. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  7. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  8. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  9. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
  10. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  11. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  12. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
9 more
  1. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  2. 2018Probabilistic Model-Agnostic Meta-Learningcited by 256
  3. 2018Low-Shot Learning from Imaginary Datacited by 181
  4. 2020Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classificationcited by 175
  5. 2020Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspectivecited by 120
  6. 2016Range Loss for Deep Face Recognition with Long-tailcited by 111
  7. 2018Incremental Few-Shot Learning with Attention Attractor Networkscited by 66
  8. 2018Feature Space Transfer for Data Augmentationcited by 21
  9. 2020Long-Tailed Recognition Using Class-Balanced Expertscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 6; 2023: 9; 2024: 8; 2025: 4; 2026: 2.

31 papers.

Sort:

By area:

  1. 2021Deep Long-Tailed Learning: A Surveycited by 417
  2. 2022A Survey on Long-Tailed Visual Recognitioncited by 75
  3. 2024A Systematic Review on Long-Tailed Learningcited by 28
  4. 2022When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Methodcited by 21
  5. 2022Improving the Intra-class Long-tail in 3D Detection via Rare Example Miningcited by 19
  6. 2024Delving into the Trajectory Long-tail Distribution for Muti-object Trackingcited by 18
  7. 2022Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-tailed Learningcited by 17
  8. 2023Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancercited by 17
  9. 2021Label-Aware Distribution Calibration for Long-tailed Classificationcited by 13
  10. 2023Transfer Knowledge from Head to Tail: Uncertainty Calibration under Long-tailed Distributioncited by 12
  11. 2024Geometric Prior Guided Feature Representation Learning for Long-Tailed Classificationcited by 10
  12. 2025A Comprehensive Survey on Imbalanced Data Learningcited by 10
19 more
  1. 2023Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifoldscited by 9
  2. 2023SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tailcited by 9
  3. 2023Learning Prototype Classifiers for Long-Tailed Recognitioncited by 6
  4. 2023Towards Heterogeneous Long-tailed Learning: Benchmarking, Metrics, and Toolboxcited by 6
  5. 2022Compound Batch Normalization for Long-tailed Image Classificationcited by 5
  6. 2023Orthogonal Uncertainty Representation of Data Manifold for Robust Long-Tailed Learningcited by 5
  7. 2022Rebalanced Siamese Contrastive Mining for Long-Tailed Recognitioncited by 4
  8. 2024VLMine: Long-Tail Data Mining with Vision Language Modelscited by 4
  9. 2023Delving Deep into Simplicity Bias for Long-Tailed Image Recognitioncited by 3
  10. 2023Data-Centric Long-Tailed Image Recognitioncited by 1
  11. 2024TaE: Task-aware Expandable Representation for Long Tail Class Incremental Learningcited by 1
  12. 2024Decoupled Federated Learning on Long-Tailed and Non-IID data with Feature Statisticscited by 1
  13. 2024Taming the Tail: Leveraging Asymmetric Loss and Pade Approximation to Overcome Medical Image Long-Tailed Class Imbalancecited by 1
  14. 2024Revisiting Long-Tailed Learning: Insights from an Architectural Perspectivecited by 1
  15. 2025Compositional Attribute Imbalance in Vision Datasetscited by 1
  16. 2026Reframing Long-Tailed Learning via Loss Landscape Geometrycited by 1
  17. 2025Calibrating Biased Distribution in VFM-derived Latent Space via Cross-Domain Geometric Consistencycited by 0
  18. 2025Optimizing Class Distributions for Bias-Aware Multi-Class Learningcited by 0
  19. 2026OFBD: Object-Focused Background Debiasing for Long-Tailed Learningcited by 0