mlsanityData to 7 Oct 2026

Taxonomic Class Incremental Learning

arXiv 2304.05547 ↗First posted 12 Apr 2023cs.LG cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

The problem of continual learning has attracted rising attention in recent years. However, few works have questioned the commonly used learning setup, based on a task curriculum of random class. This differs significantly from human continual learning, which is guided by taxonomic curricula. In this work, we propose the Taxonomic Class Incremental Learning (TCIL) problem. In TCIL, the task sequence is organized based on a taxonomic class tree. We unify existing approaches to CIL and taxonomic learning as parameter inheritance schemes and introduce a new such scheme for the TCIL learning. This enables the incremental transfer of knowledge from ancestor to descendant class of a class taxonomy through parameter inheritance. Experiments on CIFAR-100 and ImageNet-100 show the effectiveness of the proposed TCIL method, which outperforms existing SOTA methods by 2% in terms of final accuracy on CIFAR-100 and 3% on ImageNet-100.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 23 of its 42 references that are in the map. First posted on arXiv 12 Apr 2023.

Builds on

23 of 42 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  4. 2016Learning without Forgettingcited by 2,465
  5. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  6. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  7. 2016Progressive Neural Networkscited by 1,332
  8. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  9. 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 446
  10. 2016Expert Gate: Lifelong Learning with a Network of Expertscited by 369
  11. 2021DER: Dynamically Expandable Representation for Class Incremental Learningcited by 355
  12. 2021DyTox: Transformers for Continual Learning with DYnamic TOken eXpansioncited by 291
11 more
  1. 2022FOSTER: Feature Boosting and Compression for Class-Incremental Learningcited by 228
  2. 2023Progressive Prompts: Continual Learning for Language Modelscited by 195
  3. 2013Revisiting Natural Gradient for Deep Networkscited by 157
  4. 2021Training Networks in Null Space of Feature Covariance for Continual Learningcited by 139
  5. 2022Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidationcited by 113
  6. 2021On Learning the Geodesic Path for Incremental Learningcited by 85
  7. 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
  8. 2016Network of Experts for Large-Scale Image Categorizationcited by 54
  9. 2017B-CNN: Branch Convolutional Neural Network for Hierarchical Classificationcited by 37
  10. 2020Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifiercited by 34
  11. 2022Balancing Stability and Plasticity through Advanced Null Space in Continual Learningcited by 29

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1.

3 papers.

  1. 2023Incremental Generalized Category Discoverycited by 25
  2. 2024Taxonomy-Aware Continual Semantic Segmentation in Hyperbolic Spaces for Open-World Perceptioncited by 8
  3. 2023The FathomNet2023 Competition Datasetcited by 1