mlsanityData to 7 Oct 2026

Continual Object Detection: A review of definitions, strategies, and challenges

arXiv 2205.15445 ↗First posted 30 May 2022cs.CV cs.LG cs.ROcited by 25

Not on the map. Why?

Abstract (arXiv)

The field of Continual Learning investigates the ability to learn consecutive tasks without losing performance on those previously learned. Its focus has been mainly on incremental classification tasks. We believe that research in continual object detection deserves even more attention due to its vast range of applications in robotics and autonomous vehicles. This scenario is more complex than conventional classification given the occurrence of instances of classes that are unknown at the time, but can appear in subsequent tasks as a new class to be learned, resulting in missing annotations and conflicts with the background label. In this review, we analyze the current strategies proposed to tackle the problem of class-incremental object detection. Our main contributions are: (1) a short and systematic review of the methods that propose solutions to traditional incremental object detection scenarios; (2) A comprehensive evaluation of the existing approaches using a new metric to quantify the stability and plasticity of each technique in a standard way; (3) an overview of the current trends within continual object detection and a discussion of possible future research directions.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 77 of its 116 references that are in the map. First posted on arXiv 30 May 2022.

Builds on

77 of 116 references.

References · 77

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  6. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  7. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  8. 2015Fast R-CNNcited by 2,930
  9. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  10. 2016Learning without Forgettingcited by 2,465
  11. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  12. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
38 more
  1. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  2. 2016Progressive Neural Networkscited by 1,332
  3. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  4. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  5. 2017Continual Learning with Deep Generative Replaycited by 1,152
  6. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  7. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  8. 2017Lifelong Learning with Dynamically Expandable Networkscited by 689
  9. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  10. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 656
  11. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  12. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 622
  13. 2019Three scenarios for continual learningcited by 610
  14. 2019Object Detection in 20 Years: A Surveycited by 528
  15. 2019Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmarkcited by 339
  16. 2021Towards Open World Object Detectioncited by 297
  17. 2017CORe50: a New Dataset and Benchmark for Continuous Object Recognitioncited by 287
  18. 2014Towards Open World Recognitioncited by 226
  19. 2018Task-Free Continual Learningcited by 219
  20. 2017Incremental Learning of Object Detectors without Catastrophic Forgettingcited by 208
  21. 2019Compacting, Picking and Growing for Unforgetting Continual Learningcited by 207
  22. 2018Zero-Shot Object Detectioncited by 189
  23. 2019Meta-Learning Representations for Continual Learningcited by 189
  24. 2020Modeling the Background for Incremental Learning in Semantic Segmentationcited by 189
  25. 2020Understanding the Role of Training Regimes in Continual Learningcited by 177
  26. 2020PLOP: Learning without Forgetting for Continual Semantic Segmentationcited by 177
  27. 2019Class-incremental Learning via Deep Model Consolidationcited by 172
  28. 2020FCOS: A simple and strong anchor-free object detectorcited by 171
  29. 2019Uncertainty-based Continual Learning with Adaptive Regularizationcited by 144
  30. 2019Incremental Learning Techniques for Semantic Segmentationcited by 141
  31. 2021Avalanche: an End-to-End Library for Continual Learningcited by 124
  32. 2020A Comprehensive Study of Class Incremental Learning Algorithms for Visual Taskscited by 107
  33. 2020Incremental Few-Shot Object Detectioncited by 102
  34. 2019Meta-Learning with Warped Gradient Descentcited by 98
  35. 2019Latent Replay for Real-Time Continual Learningcited by 97
  36. 2020iTAML: An Incremental Task-Agnostic Meta-learning Approachcited by 90
  37. 2020A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learningcited by 86
  38. 2019AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligencecited by 84

50 most cited of 77 All 77 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 9; 2024: 8; 2025: 5; 2026: 2.

25 papers.

Sort:

  1. 2024Towards Lifelong Learning of Large Language Models: A Surveycited by 60
  2. 2023A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Applicationcited by 21
  3. 2023Remote Sensing Object Detection Meets Deep Learning: A Meta-review of Challenges and Advancescited by 20
  4. 2023Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detectioncited by 14
  5. 2025MCITlib: Multimodal Continual Instruction Tuning Library and Benchmarkcited by 10
  6. 2023Adaptive Visual Scene Understanding: Incremental Scene Graph Generationcited by 6
  7. 2024Replay Consolidation with Label Propagation for Continual Object Detectioncited by 6
  8. 2025RICO: Two Realistic Benchmarks and an In-Depth Analysis for Incremental Learning in Object Detectioncited by 5
  9. 2024Modality Translation for Object Detection Adaptation Without Forgetting Prior Knowledgecited by 4
  10. 2024Latent Distillation for Continual Object Detection at the Edgecited by 4
  11. 20223rd Continual Learning Workshop Challenge on Egocentric Category and Instance Level Object Understandingcited by 3
  12. 2023MS23D: A 3D Object Detection Method Using Multi-Scale Semantic Feature Points to Construct 3D Feature Layercited by 3
13 more
  1. 2024Characterizing Continual Learning Scenarios and Strategies for Audio Analysiscited by 3
  2. 2023Class-Incremental Learning of Plant and Disease Detection: Growing Branches with Knowledge Distillationcited by 2
  3. 2024TiROD: Tiny Robotics Dataset and Benchmark for Continual Object Detectioncited by 2
  4. 2025Incremental Object Detection with Prompt-based Methodscited by 2
  5. 2023Dynamic Y-KD: A Hybrid Approach to Continual Instance Segmentationcited by 1
  6. 2023Accurate deep learning sub-grid scale models for large eddy simulationscited by 1
  7. 2023MultIOD: Rehearsal-free Multihead Incremental Object Detectorcited by 1
  8. 2025Teach YOLO to Remember: A Self-Distillation Approach for Continual Object Detectioncited by 1
  9. 2025DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmeticcited by 1
  10. 2026Learning on the Fly: Replay-Based Continual Object Perception for Indoor Dronescited by 1
  11. 2024Efficient Parameter Mining and Freezing for Continual Object Detectioncited by 0
  12. 2024Continual Learning for Robust Gate Detection under Dynamic Lighting in Autonomous Drone Racingcited by 0
  13. 2026MECAIL: Communication-Aware Incremental Learning for Object Detection with 14.6 KB Spatiotemporal Expertscited by 0