mlsanityData to 14 Oct 2026

Lifelong Twin Generative Adversarial Networks

arXiv 2107.04708 ↗First posted 9 Jul 2021cs.CV cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a new continuously learning generative model, called the Lifelong Twin Generative Adversarial Networks (LT-GANs). LT-GANs learns a sequence of tasks from several databases and its architecture consists of three components: two identical generators, namely the Teacher and Assistant, and one Discriminator. In order to allow for the LT-GANs to learn new concepts without forgetting, we introduce a new lifelong training approach, namely Lifelong Adversarial Knowledge Distillation (LAKD), which encourages the Teacher and Assistant to alternately teach each other, while learning a new database. This training approach favours transferring knowledge from a more knowledgeable player to another player which knows less information about a previously given task.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 13 of its 25 references that are in the map. First posted on arXiv 9 Jul 2021.

Builds on

13 of 25 references.

References · 13

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2013Auto-Encoding Variational Bayescited by 4,053
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  4. 2017Improved Training of Wasserstein GANscited by 2,235
  5. 2018Efficient Lifelong Learning with A-GEMcited by 1,058
  6. 2017Lifelong Learning with Dynamically Expandable Networkscited by 694
  7. 2017DualGAN: Unsupervised Dual Learning for Image-to-Image Translationcited by 310
  8. 2016Coupled Generative Adversarial Networkscited by 216
  9. 2021Towards Understanding Knowledge Distillationcited by 158
  10. 2019Continual Unsupervised Representation Learningcited by 147
  11. 2018Memory Replay GANs: learning to generate images from new categories without forgettingcited by 77
  12. 2017Lifelong Generative Modelingcited by 51
1 more
  1. 2020Learning latent representations across multiple data domains using Lifelong VAEGANcited by 35

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 3; 2023: 0; 2024: 0; 2025: 1.

6 papers.

  1. 2022Task-Free Continual Learning via Online Discrepancy Distance Learningcited by 22
  2. 2022Continual Variational Autoencoder Learning via Online Cooperative Memorizationcited by 12
  3. 2021Lifelong Infinite Mixture Model Based on Knowledge-Driven Dirichlet Processcited by 7
  4. 2021Lifelong Generative Modelling Using Dynamic Expansion Graph Modelcited by 4
  5. 2022Learning an evolved mixture model for task-free continual learningcited by 3
  6. 2025CCD: Continual Consistency Diffusion for Lifelong Generative Modelingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Lifelong Teacher-Student Network Learning
  2. 2021Training Generative Adversarial Networks in One Stage
  3. 2023KD-DLGAN: Data Limited Image Generation via Knowledge Distillation
  4. 2025TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows
  5. 2021Evolutionary Generative Adversarial Networks with Crossover Based Knowledge Distillation
  6. 2026Improving Generative Adversarial Networks with Self-Distillation
  7. 2026Logic Tensor Network-Enhanced Generative Adversarial Network
  8. 2025SDAKD: Student Discriminator Assisted Knowledge Distillation for Super-Resolution Generative Adversarial Networks