mlsanityData to 7 Oct 2026

Dynamic VAEs with Generative Replay for Continual Zero-shot Learning

arXiv 2104.12468 ↗First posted 26 Apr 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Continual zero-shot learning(CZSL) is a new domain to classify objects sequentially the model has not seen during training. It is more suitable than zero-shot and continual learning approaches in real-case scenarios when data may come continually with only attributes for a few classes and attributes and features for other classes. Continual learning(CL) suffers from catastrophic forgetting, and zero-shot learning(ZSL) models cannot classify objects like state-of-the-art supervised classifiers due to lack of actual data(or features) during training. This paper proposes a novel continual zero-shot learning (DVGR-CZSL) model that grows in size with each task and uses generative replay to update itself with previously learned classes to avoid forgetting. We demonstrate our hybrid model(DVGR-CZSL) outperforms the baselines and is effective on several datasets, i.e., CUB, AWA1, AWA2, and aPY. We show our method is superior in task sequentially learning with ZSL(Zero-Shot Learning). We also discuss our results on the SUN dataset.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 25 of its 37 references that are in the map. First posted on arXiv 26 Apr 2021.

Builds on

25 of 37 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  5. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  6. 2016Progressive Neural Networkscited by 1,332
  7. 2017Continual Learning with Deep Generative Replaycited by 1,152
  8. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,094
  9. 2018Efficient Lifelong Learning with A-GEMcited by 1,044
  10. 2019Large Scale Incremental Learningcited by 727
  11. 2017Lifelong Learning with Dynamically Expandable Networkscited by 689
  12. 2018Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interferencecited by 511
13 more
  1. 2017Variational Continual Learningcited by 335
  2. 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 254
  3. 2017FearNet: Brain-Inspired Model for Incremental Learningcited by 177
  4. 2018Memory Efficient Experience Replay for Streaming Learningcited by 128
  5. 2018Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgettingcited by 127
  6. 2018Memory Replay GANs: learning to generate images from new categories without forgettingcited by 76
  7. 2020Generalized Variational Continual Learningcited by 56
  8. 2017A Simple Exponential Family Framework for Zero-Shot Learningcited by 38
  9. 2017Zero-Shot Learning via Class-Conditioned Deep Generative Modelscited by 21
  10. 2020Generalized Continual Zero-Shot Learningcited by 7
  11. 2021Generative Replay-based Continual Zero-Shot Learningcited by 7
  12. 2020Class Normalization for (Continual)? Generalized Zero-Shot Learningcited by 5
  13. 2021Adversarial Training of Variational Auto-encoders for Continual Zero-shot Learning(A-CZSL)cited by 5

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 2.

5 papers.

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  2. 2022Unseen Classes at a Later Time? No Problemcited by 7
  3. 2021Domain-Aware Continual Zero-Shot Learningcited by 3
  4. 2022Evolutionary Generalized Zero-Shot Learningcited by 3
  5. 2023Continual Zero-Shot Learning through Semantically Guided Generative Random Walkscited by 2