mlsanityData to 14 Oct 2026

Incremental Learning of Object Detectors without Catastrophic Forgetting

arXiv 1708.06977 ↗First posted 23 Aug 2017cs.CVcited by 208

Not on the map. Why?

Abstract (arXiv)

Despite their success for object detection, convolutional neural networks are ill-equipped for incremental learning, i.e., adapting the original model trained on a set of classes to additionally detect objects of new classes, in the absence of the initial training data. They suffer from "catastrophic forgetting" - an abrupt degradation of performance on the original set of classes, when the training objective is adapted to the new classes. We present a method to address this issue, and learn object detectors incrementally, when neither the original training data nor annotations for the original classes in the new training set are available. The core of our proposed solution is a loss function to balance the interplay between predictions on the new classes and a new distillation loss which minimizes the discrepancy between responses for old classes from the original and the updated networks. This incremental learning can be performed multiple times, for a new set of classes in each step, with a moderate drop in performance compared to the baseline network trained on the ensemble of data. We present object detection results on the PASCAL VOC 2007 and COCO datasets, along with a detailed empirical analysis of the approach.

Key facts. Cited by 208 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 45; 2022: 43; 2023: 44; 2024: 33; 2025: 22; 2026: 21.

208 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  2. 2021Towards Open World Object Detectioncited by 297
  3. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 245
  4. 2023Class-Incremental Learning: A Surveycited by 209
  5. 2023SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Modelcited by 180
  6. 2021OW-DETR: Open-world Detection Transformercited by 129
  7. 2022Federated Class-Incremental Learningcited by 127
  8. 2021AutoNovel: Automatically Discovering and Learning Novel Visual Categoriescited by 116
  9. 2021Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learningcited by 115
  10. 2021Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representationscited by 96
  11. 2021RECALL: Replay-based Continual Learning in Semantic Segmentationcited by 83
  12. 2022Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillationcited by 72
38 more
  1. 2023Continual Detection Transformer for Incremental Object Detectioncited by 59
  2. 2021Lifelong Person Re-Identification via Adaptive Knowledge Accumulationcited by 57
  3. 2022PROB: Probabilistic Objectness for Open World Object Detectioncited by 57
  4. 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
  5. 2021Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Typescited by 54
  6. 2021Self-Supervised Training Enhances Online Continual Learningcited by 54
  7. 2023No One Left Behind: Real-World Federated Class-Incremental Learningcited by 53
  8. 2021Layerwise Optimization by Gradient Decomposition for Continual Learningcited by 51
  9. 2023A Survey on Few-Shot Class-Incremental Learningcited by 48
  10. 2022Class-Incremental Learning for Action Recognition in Videoscited by 46
  11. 2024SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detectioncited by 44
  12. 2022Memory Efficient Continual Learning with Transformerscited by 43
  13. 2022On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learningcited by 39
  14. 2022Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentationcited by 37
  15. 2022Energy-based Latent Aligner for Incremental Learningcited by 37
  16. 2021Multi-View Correlation Distillation for Incremental Object Detectioncited by 36
  17. 2022CLAD: A realistic Continual Learning benchmark for Autonomous Drivingcited by 36
  18. 2021Wanderlust: Online Continual Object Detection in the Real Worldcited by 34
  19. 2023Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detectioncited by 32
  20. 2022Revisiting Open World Object Detectioncited by 30
  21. 2022Learning with Recoverable Forgettingcited by 30
  22. 2022Open-world Semantic Segmentation for LIDAR Point Cloudscited by 29
  23. 2023CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detectioncited by 28
  24. 2021Dynamic Language Models for Continuously Evolving Contentcited by 27
  25. 2023Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learningcited by 26
  26. 2023Teacher-Student Architecture for Knowledge Distillation: A Surveycited by 26
  27. 2024AIDE: An Automatic Data Engine for Object Detection in Autonomous Drivingcited by 26
  28. 2021Optimizing Reusable Knowledge for Continual Learning via Metalearningcited by 25
  29. 2021Continual Semi-Supervised Learning through Contrastive Interpolation Consistencycited by 25
  30. 2022Continual Object Detection: A review of definitions, strategies, and challengescited by 25
  31. 2022Modeling Missing Annotations for Incremental Learning in Object Detectioncited by 23
  32. 2023FedET: A Communication-Efficient Federated Class-Incremental Learning Framework Based on Enhanced Transformercited by 23
  33. 2024VLM-PL: Advanced Pseudo Labeling Approach for Class Incremental Object Detection via Vision-Language Modelcited by 23
  34. 2022Interactron: Embodied Adaptive Object Detectioncited by 21
  35. 2022Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentationcited by 21
  36. 2022Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanismcited by 20
  37. 2022Learning Incrementally to Segment Multiple Organs in a CT Imagecited by 19
  38. 2021Objects in Semantic Topologycited by 18

50 most cited of 208 All 208 (JSON)