mlsanityData to 14 Oct 2026

A Procedural World Generation Framework for Systematic Evaluation of Continual Learning

arXiv 2106.02585 ↗First posted 4 Jun 2021cs.LG cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Several families of continual learning techniques have been proposed to alleviate catastrophic interference in deep neural network training on non-stationary data. However, a comprehensive comparison and analysis of limitations remains largely open due to the inaccessibility to suitable datasets. Empirical examination not only varies immensely between individual works, it further currently relies on contrived composition of benchmarks through subdivision and concatenation of various prevalent static vision datasets. In this work, our goal is to bridge this gap by introducing a computer graphics simulation framework that repeatedly renders only upcoming urban scene fragments in an endless real-time procedural world generation process. At its core lies a modular parametric generative model with adaptable generative factors. The latter can be used to flexibly compose data streams, which significantly facilitates a detailed analysis and allows for effortless investigation of various continual learning schemes.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 42 of its 83 references that are in the map. First posted on arXiv 4 Jun 2021.

Builds on

42 of 83 references.

References · 42

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  6. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  7. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  8. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  9. 2016Learning without Forgettingcited by 2,496
  10. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  11. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  12. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
30 more
  1. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  2. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  3. 2017Continual Learning with Deep Generative Replaycited by 1,158
  4. 2018Experience Replay for Continual Learningcited by 1,095
  5. 2016Playing for Data: Ground Truth from Computer Gamescited by 818
  6. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 742
  7. 2017Learning multiple visual domains with residual adapterscited by 557
  8. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  9. 2017Measuring Catastrophic Forgetting in Neural Networkscited by 360
  10. 2017Variational Continual Learningcited by 339
  11. 2017CORe50: a New Dataset and Benchmark for Continuous Object Recognitioncited by 289
  12. 2016Learning from Simulated and Unsupervised Images through Adversarial Trainingcited by 288
  13. 2018A Probabilistic U-Net for Segmentation of Ambiguous Imagescited by 283
  14. 2018Selective Experience Replay for Lifelong Learningcited by 241
  15. 2015Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understandingcited by 218
  16. 2018Towards Robust Evaluations of Continual Learningcited by 148
  17. 2021Avalanche: an End-to-End Library for Continual Learningcited by 124
  18. 2018Don't forget, there is more than forgetting: new metrics for Continual Learningcited by 115
  19. 2017Encoder Based Lifelong Learningcited by 102
  20. 2020A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learningcited by 87
  21. 2019Lifelong GAN: Continual Learning for Conditional Image Generationcited by 78
  22. 2018Generative Models from the perspective of Continual Learningcited by 69
  23. 2017Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Studycited by 46
  24. 2018Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologiescited by 43
  25. 2018Effective Use of Synthetic Data for Urban Scene Semantic Segmentationcited by 41
  26. 2019A comprehensive, application-oriented study of catastrophic forgetting in DNNscited by 35
  27. 2016Procedural Generation of Videos to Train Deep Action Recognition Networkscited by 31
  28. 2015SceneNet: Understanding Real World Indoor Scenes With Synthetic Datacited by 29
  29. 2019Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognitioncited by 26
  30. 2017Adversarially Tuned Scene Generationcited by 5

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 1.

4 papers.

  1. 2023Designing a Hybrid Neural System to Learn Real-world Crack Segmentation from Fractal-based Simulationcited by 10
  2. 2024Where is the Truth? The Risk of Getting Confounded in a Continual Worldcited by 8
  3. 2022Lifelong Wandering: A realistic few-shot online continual learning settingcited by 1
  4. 2025synth-dacl: Does Synthetic Defect Data Enhance Segmentation Accuracy and Robustness for Real-World Bridge Inspections?cited by 0