mlsanityData to 7 Oct 2026

Semi-Supervised Learning with Taxonomic Labels

arXiv 2111.11595 ↗First posted 23 Nov 2021cs.CV cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

We propose techniques to incorporate coarse taxonomic labels to train image classifiers in fine-grained domains. Such labels can often be obtained with a smaller effort for fine-grained domains such as the natural world where categories are organized according to a biological taxonomy. On the Semi-iNat dataset consisting of 810 species across three Kingdoms, incorporating Phylum labels improves the Species level classification accuracy by 6% in a transfer learning setting using ImageNet pre-trained models. Incorporating the hierarchical label structure with a state-of-the-art semi-supervised learning algorithm called FixMatch improves the performance further by 1.3%. The relative gains are larger when detailed labels such as Class or Order are provided, or when models are trained from scratch. However, we find that most methods are not robust to the presence of out-of-domain data from novel classes. We propose a technique to select relevant data from a large collection of unlabeled images guided by the hierarchy which improves the robustness. Overall, our experiments show that semi-supervised learning with coarse taxonomic labels are practical for training classifiers in fine-grained domains.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 36 of its 53 references that are in the map. First posted on arXiv 23 Nov 2021.

Builds on

36 of 53 references.

References · 36

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  7. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  8. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  9. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  10. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  11. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
  12. 2016YOLO9000: Better, Faster, Strongercited by 1,429
24 more
  1. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  2. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  3. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  4. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  5. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  6. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  7. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  8. 2020Rethinking Pre-training and Self-trainingcited by 352
  9. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  10. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  11. 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
  12. 2015Semi-Supervised Learning with Ladder Networkscited by 246
  13. 2014Learning with Pseudo-Ensemblescited by 241
  14. 2019Billion-scale semi-supervised learning for image classificationcited by 232
  15. 2019Boosting Few-Shot Visual Learning with Self-Supervisioncited by 140
  16. 2021When Does Contrastive Visual Representation Learning Work?cited by 92
  17. 2019When Does Self-supervision Improve Few-shot Learning?cited by 78
  18. 2020Grafit: Learning fine-grained image representations with coarse labelscited by 43
  19. 2017B-CNN: Branch Convolutional Neural Network for Hierarchical Classificationcited by 37
  20. 2021A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classificationcited by 36
  21. 2020Fine-grained Angular Contrastive Learning with Coarse Labelscited by 30
  22. 2018Hierarchical Novelty Detection for Visual Object Recognitioncited by 26
  23. 2021The Semi-Supervised iNaturalist Challenge at the FGVC8 Workshopcited by 16
  24. 2020Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learningcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 6; 2024: 0; 2025: 1; 2026: 2.

11 papers.

  1. 2022Learning Hierarchy Aware Features for Reducing Mistake Severitycited by 26
  2. 2023TransHP: Image Classification with Hierarchical Promptingcited by 16
  3. 2022Continual Learning with Evolving Class Ontologiescited by 13
  4. 2023RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Datacited by 10
  5. 2023Test-Time Amendment with a Coarse Classifier for Fine-Grained Classificationcited by 5
  6. 2025Global and Local Entailment Learning for Natural World Imagerycited by 3
  7. 2023LiT Tuned Models for Efficient Species Detectioncited by 1
  8. 2023TaxoKnow: Taxonomy as Prior Knowledge in the Loss Function of Multi-class Classificationcited by 1
  9. 2026Extremely coarse learning objectives induce human-aligned representations in AI vision modelscited by 1
  10. 2023SemiGPC: Distribution-Aware Label Refinement for Imbalanced Semi-Supervised Learning Using Gaussian Processescited by 0
  11. 2026Taxonomy-aware deep learning for hierarchical marine species classification in underwater imagerycited by 0