mlsanityData to 7 Oct 2026

CLAD: A realistic Continual Learning benchmark for Autonomous Driving

arXiv 2210.03482 ↗First posted 7 Oct 2022cs.CV cs.LGcited by 35

Not on the map. Why?

Abstract (arXiv)

In this paper we describe the design and the ideas motivating a new Continual Learning benchmark for Autonomous Driving (CLAD), that focuses on the problems of object classification and object detection. The benchmark utilises SODA10M, a recently released large-scale dataset that concerns autonomous driving related problems. First, we review and discuss existing continual learning benchmarks, how they are related, and show that most are extreme cases of continual learning. To this end, we survey the benchmarks used in continual learning papers at three highly ranked computer vision conferences. Next, we introduce CLAD-C, an online classification benchmark realised through a chronological data stream that poses both class and domain incremental challenges; and CLAD-D, a domain incremental continual object detection benchmark. We examine the inherent difficulties and challenges posed by the benchmark, through a survey of the techniques and methods used by the top-3 participants in a CLAD-challenge workshop at ICCV 2021. We conclude with possible pathways to improve the current continual learning state of the art, and which directions we deem promising for future research.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 53 of its 74 references that are in the map. First posted on arXiv 7 Oct 2022.

Builds on

53 of 74 references.

References · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  6. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  7. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  8. 2016Densely Connected Convolutional Networkscited by 6,691
  9. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  10. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  11. 2016Learning without Forgettingcited by 2,465
  12. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
38 more
  1. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  2. 2019Natural Adversarial Examplescited by 1,401
  3. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  4. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  5. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
  6. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  7. 2019When Does Label Smoothing Help?cited by 985
  8. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  9. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 895
  10. 2019Three scenarios for continual learningcited by 610
  11. 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 430
  12. 2019Online Continual Learning with Maximally Interfered Retrievalcited by 376
  13. 2021DyTox: Transformers for Continual Learning with DYnamic TOken eXpansioncited by 291
  14. 2017CORe50: a New Dataset and Benchmark for Continuous Object Recognitioncited by 287
  15. 2021Rainbow Memory: Continual Learning with a Memory of Diverse Samplescited by 273
  16. 2021Co2L: Contrastive Continual Learningcited by 243
  17. 2015YFCC100M: The New Data in Multimedia Researchcited by 234
  18. 2018Task-Free Continual Learningcited by 219
  19. 2017Incremental Learning of Object Detectors without Catastrophic Forgettingcited by 208
  20. 2021Vision Transformers are Robust Learnerscited by 208
  21. 2020PLOP: Learning without Forgetting for Continual Semantic Segmentationcited by 177
  22. 2020Continual Prototype Evolution: Learning Online from Non-Stationary Data Streamscited by 143
  23. 2021An Empirical Investigation of the Role of Pre-training in Lifelong Learningcited by 134
  24. 2021Online Coreset Selection for Rehearsal-based Continual Learningcited by 114
  25. 2018Continuous Learning in Single-Incremental-Task Scenarioscited by 109
  26. 2022The CLEAR Benchmark: Continual LEArning on Real-World Imagerycited by 92
  27. 2019Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysiscited by 91
  28. 2020GAN Memory with No Forgettingcited by 84
  29. 2021Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Datacited by 67
  30. 2020Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNNcited by 61
  31. 2022Class-Incremental Learning with Strong Pre-trained Modelscited by 60
  32. 2020Incremental Object Detection via Meta-Learningcited by 58
  33. 2021Self-Supervised Training Enhances Online Continual Learningcited by 53
  34. 2022Architecture Matters in Continual Learningcited by 46
  35. 2021Understanding Continual Learning Settings with Data Distribution Drift Analysiscited by 38
  36. 2021Wanderlust: Online Continual Object Detection in the Real Worldcited by 34
  37. 2019OpenLORIS-Object: A Robotic Vision Dataset and Benchmark for Lifelong Deep Learningcited by 28
  38. 2022Towards Exemplar-Free Continual Learning in Vision Transformers: an Account of Attention, Functional and Weight Regularizationcited by 23

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 8; 2024: 9; 2025: 14; 2026: 3.

35 papers.

Sort:

By area:

  1. 2023TiC-CLIP: Continual Training of CLIP Modelscited by 38
  2. 2023Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learningcited by 34
  3. 2025Vision-Language-Action Models for Autonomous Driving: Past, Present, and Futurecited by 32
  4. 2024Beyond Prompt Learning: Continual Adapter for Efficient Rehearsal-Free Continual Learningcited by 29
  5. 2024A Practitioner's Guide to Continual Multimodal Pretrainingcited by 22
  6. 2025Optimal Task Order for Continual Learning of Multiple Taskscited by 14
  7. 2025Parameter-Efficient Continual Fine-Tuning: A Surveycited by 11
  8. 2024Continual Learning in the Presence of Repetitioncited by 10
  9. 2023AR-TTA: A Simple Method for Real-World Continual Test-Time Adaptationcited by 8
  10. 2025DualCP: Rehearsal-Free Domain-Incremental Learning via Dual-Level Concept Prototypecited by 7
  11. 2026FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability-Plasticity Tradeoffcited by 7
  12. 2024Replay Consolidation with Label Propagation for Continual Object Detectioncited by 6
23 more
  1. 2025RICO: Two Realistic Benchmarks and an In-Depth Analysis for Incremental Learning in Object Detectioncited by 5
  2. 2025PLAN: Proactive Low-Rank Allocation for Continual Learningcited by 5
  3. 2023ScrollNet: Dynamic Weight Importance for Continual Learningcited by 4
  4. 2024Online Analytic Exemplar-Free Continual Learning with Large Models for Imbalanced Autonomous Driving Taskcited by 4
  5. 2025Continual Hyperbolic Learning of Instances and Classescited by 4
  6. 20223rd Continual Learning Workshop Challenge on Egocentric Category and Instance Level Object Understandingcited by 3
  7. 2023Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalizationcited by 3
  8. 2024CEL: A Continual Learning Model for Disease Outbreak Prediction by Leveraging Domain Adaptation via Elastic Weight Consolidationcited by 3
  9. 2025Global Convergence of Continual Learning on Non-IID Datacited by 3
  10. 2024Lifelong Learning of Video Diffusion Models From a Single Video Streamcited by 2
  11. 2024TiROD: Tiny Robotics Dataset and Benchmark for Continual Object Detectioncited by 2
  12. 2026A Practical Guide to Streaming Continual Learningcited by 2
  13. 2023TADIL: Task-Agnostic Domain-Incremental Learning through Task-ID Inference using Transformer Nearest-Centroid Embeddingscited by 1
  14. 2023EgoAdapt: A multi-stream evaluation study of adaptation to real-world egocentric user videocited by 1
  15. 2025CRAM: Large-scale Video Continual Learning with Bootstrapped Compressioncited by 1
  16. 2025Chat with UAV -- Human-UAV Interaction Based on Large Language Modelscited by 1
  17. 2023Continual Cross-Dataset Adaptation in Road Surface Classificationcited by 0
  18. 2024Continual Learning for Adaptable Car-Following in Dynamic Traffic Environmentscited by 0
  19. 2025Enhancing knowledge retention for continual learning with domain-specific adapters and features gatingcited by 0
  20. 2025Semi-parametric Memory Consolidation: Towards Brain-like Deep Continual Learningcited by 0
  21. 2025GradMix: Gradient-based Selective Mixup for Robust Data Augmentation in Class-Incremental Learningcited by 0
  22. 2025Monte Carlo Functional Regularisation for Continual Learningcited by 0
  23. 2026A Survey on End-to-End Autonomous Driving Training from the Perspectives of Data, Strategy, and Platformcited by 0