mlsanityData to 14 Oct 2026

The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition

arXiv 1511.06789 ↗First posted 20 Nov 2015cs.CVcited by 48

Not on the map. Why?

Abstract (arXiv)

Current approaches for fine-grained recognition do the following: First, recruit experts to annotate a dataset of images, optionally also collecting more structured data in the form of part annotations and bounding boxes. Second, train a model utilizing this data. Toward the goal of solving fine-grained recognition, we introduce an alternative approach, leveraging free, noisy data from the web and simple, generic methods of recognition. This approach has benefits in both performance and scalability. We demonstrate its efficacy on four fine-grained datasets, greatly exceeding existing state of the art without the manual collection of even a single label, and furthermore show first results at scaling to more than 10,000 fine-grained categories. Quantitatively, we achieve top-1 accuracies of 92.3% on CUB-200-2011, 85.4% on Birdsnap, 93.4% on FGVC-Aircraft, and 80.8% on Stanford Dogs without using their annotated training sets. We compare our approach to an active learning approach for expanding fine-grained datasets.

Key facts. Cited by 48 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Nov 2015.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 18; 2022: 9; 2023: 11; 2024: 7; 2025: 3.

48 papers.

Sort:

By area:

  1. 2021Benchmarking Representation Learning for Natural World Image Collectionscited by 168
  2. 2021Fine-Grained Image Analysis with Deep Learning: A Surveycited by 135
  3. 2021Playing for 3D Human Recoverycited by 64
  4. 2022Webly Supervised Concept Expansion for General Purpose Vision Modelscited by 45
  5. 2021Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classificationcited by 31
  6. 2021Danish Fungi 2020 -- Not Just Another Image Recognition Datasetcited by 27
  7. 2021Improving Fractal Pre-trainingcited by 26
  8. 2023PDiscoNet: Semantically consistent part discovery for fine-grained recognitioncited by 21
  9. 2025The iNaturalist Sounds Datasetcited by 17
  10. 2021An Instance-Dependent Simulation Framework for Learning with Label Noisecited by 14
  11. 2022Exploring Fine-Grained Audiovisual Categorization with the SSW60 Datasetcited by 12
  12. 2022Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-Boosting Attention Mechanismcited by 12
36 more
  1. 2021Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognitioncited by 11
  2. 2023A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptationcited by 11
  3. 2021EfficientCLIP: Efficient Cross-Modal Pre-training by Ensemble Confident Learning and Language Modelingcited by 10
  4. 2021The Curious Layperson: Fine-Grained Image Recognition without Expert Labelscited by 7
  5. 2024PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneckcited by 7
  6. 2023Deep Learning Pipeline for Automated Visual Moth Monitoring: Insect Localization and Species Classificationcited by 5
  7. 2023From Categories to Classifiers: Name-Only Continual Learning by Exploring the Webcited by 5
  8. 2024PLReMix: Combating Noisy Labels with Pseudo-Label Relaxed Contrastive Representation Learningcited by 5
  9. 2021Multiplicative Reweighting for Robust Neural Network Optimizationcited by 4
  10. 2021Fine-Grained Adversarial Semi-supervised Learningcited by 4
  11. 2023Combining Deep Learning and Street View Imagery to Map Smallholder Crop Typescited by 4
  12. 2024Learning with Noisy Labels: Interconnection of Two Expectation-Maximizationscited by 4
  13. 2022Active Labeling: Streaming Stochastic Gradientscited by 3
  14. 2023Reduction of Class Activation Uncertainty with Background Informationcited by 3
  15. 2023CAPro: Webly Supervised Learning with Cross-Modality Aligned Prototypescited by 3
  16. 2024Curriculum Fine-tuning of Vision Foundation Model for Medical Image Classification Under Label Noisecited by 3
  17. 2021Learning from Crowds with Sparse and Imbalanced Annotationscited by 2
  18. 2021Towards Robust Cross-domain Image Understanding with Unsupervised Noise Removalcited by 2
  19. 2022Deep Image Retrieval is not Robust to Label Noisecited by 2
  20. 2023Simplified Concrete Dropout -- Improving the Generation of Attribution Masks for Fine-grained Classificationcited by 2
  21. 2021cofga: A Dataset for Fine Grained Classification of Objects from Aerial Imagerycited by 1
  22. 2022PENCIL: Deep Learning with Noisy Labelscited by 1
  23. 2022FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical Learningcited by 1
  24. 2023Practical Knowledge Distillation: Using DNNs to Beat DNNscited by 1
  25. 2023Cascading Hierarchical Networks with Multi-task Balanced Loss for Fine-grained hashingcited by 1
  26. 2024Mitigating the Impact of Labeling Errors on Training via Rockafellian Relaxationcited by 1
  27. 2024Precision at Scale: Domain-Specific Datasets On-Demandcited by 1
  28. 2025Plant identification based on noisy web data: the amazing performance of deep learning (LifeCLEF 2017)cited by 1
  29. 2021INN: A Method Identifying Clean-annotated Samples via Consistency Effect in Deep Neural Networkscited by 0
  30. 2021Learning a Discriminant Latent Space with Neural Discriminant Analysiscited by 0
  31. 2021Weak Novel Categories without Tears: A Survey on Weak-Shot Learningcited by 0
  32. 2022Elucidating Meta-Structures of Noisy Labels in Semantic Segmentation by Deep Neural Networkscited by 0
  33. 2022When & How to Transfer with Transfer Learningcited by 0
  34. 2023Sample selection with noise rate estimation in noise learning of medical image analysiscited by 0
  35. 2024FathomVerse: A community science dataset for ocean animal discoverycited by 0
  36. 2025Overview of LifeCLEF Plant Identification task 2019: diving into data deficient tropical countriescited by 0