mlsanityData to 7 Oct 2026

Grafit: Learning fine-grained image representations with coarse labels

arXiv 2011.12982 ↗First posted 25 Nov 2020cs.CVcited by 43

Not on the map. Why?

Abstract (arXiv)

This paper tackles the problem of learning a finer representation than the one provided by training labels. This enables fine-grained category retrieval of images in a collection annotated with coarse labels only. Our network is learned with a nearest-neighbor classifier objective, and an instance loss inspired by self-supervised learning. By jointly leveraging the coarse labels and the underlying fine-grained latent space, it significantly improves the accuracy of category-level retrieval methods. Our strategy outperforms all competing methods for retrieving or classifying images at a finer granularity than that available at train time. It also improves the accuracy for transfer learning tasks to fine-grained datasets, thereby establishing the new state of the art on five public benchmarks, like iNaturalist-2018.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 10; 2023: 12; 2024: 6; 2025: 1; 2026: 1.

43 papers.

Sort:

By area:

  1. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  2. 2021Transformer in Transformercited by 632
  3. 2022DeiT III: Revenge of the ViTcited by 417
  4. 2021ResNet strikes back: An improved training procedure in timmcited by 365
  5. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 338
  6. 2021Incorporating Convolution Designs into Visual Transformerscited by 248
  7. 2021ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Biascited by 216
  8. 2021AutoFormer: Searching Transformers for Visual Recognitioncited by 186
  9. 2021Instance-Conditioned GANcited by 119
  10. 2022ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyondcited by 117
  11. 2022Retrieval Augmented Classification for Long-Tail Visual Recognitioncited by 106
  12. 2022MiniViT: Compressing Vision Transformers with Weight Multiplexingcited by 88
31 more
  1. 2023GeneCIS: A Benchmark for General Conditional Image Similaritycited by 46
  2. 2023Towards In-context Scene Understandingcited by 45
  3. 2022Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domainscited by 42
  4. 2023Vocabulary-free Image Classificationcited by 35
  5. 2021Augmenting Convolutional networks with attention-based aggregationcited by 29
  6. 2022MetaFormer: A Unified Meta Framework for Fine-Grained Recognitioncited by 28
  7. 2021Efficient Algorithms for Learning from Coarse Labelscited by 21
  8. 2023MaskCon: Masked Contrastive Learning for Coarse-Labelled Datasetcited by 21
  9. 2024CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scalecited by 18
  10. 2022Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal Informationcited by 15
  11. 2022On Label Granularity and Object Localizationcited by 12
  12. 2024DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTscited by 12
  13. 2021Semi-Supervised Learning with Taxonomic Labelscited by 11
  14. 2023Quantifying the Variability Collapse of Neural Networkscited by 9
  15. 2023Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labelscited by 8
  16. 2024Vocabulary-free Image Classification and Semantic Segmentationcited by 8
  17. 2021Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learningcited by 7
  18. 2022It's All in the Head: Representation Knowledge Distillation through Classifier Sharingcited by 7
  19. 2021Rethinking Nearest Neighbors for Visual Classificationcited by 6
  20. 2023Weakly Supervised Temporal Convolutional Networks for Fine-grained Surgical Activity Recognitioncited by 5
  21. 2023Weakly Supervised Lesion Detection and Diagnosis for Breast Cancers with Partially Annotated Ultrasound Imagescited by 5
  22. 2023Learn More for Food Recognition via Progressive Self-Distillationcited by 4
  23. 2023Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifoldcited by 3
  24. 2024Fine-grained Classes and How to Find Themcited by 2
  25. 2023EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attentioncited by 1
  26. 2024Progressive Multi-task Anti-Noise Learning and Distilling Frameworks for Fine-grained Vehicle Recognitioncited by 1
  27. 2025Twofold Debiasing Enhances Fine-Grained Learning with Coarse Labelscited by 1
  28. 2022FedMT: Federated Learning with Mixed-type Labelscited by 0
  29. 2023ELFIS: Expert Learning for Fine-grained Image Recognition Using Subsetscited by 0
  30. 2024Fine-grained Classification of Port Wine Stains Using Optical Coherence Tomography Angiographycited by 0
  31. 2026Spatial-Temporal Expert Learning for Video-based Person Re-identificationcited by 0