mlsanityData to 14 Oct 2026

Modeling Missing Annotations for Incremental Learning in Object Detection

arXiv 2204.08766 ↗First posted 19 Apr 2022cs.CVcited by 23

On the map: Knowledge distillation → Detection and dense prediction distillation

Abstract (arXiv)

Despite the recent advances in the field of object detection, common architectures are still ill-suited to incrementally detect new categories over time. They are vulnerable to catastrophic forgetting: they forget what has been already learned while updating their parameters in absence of the original training data. Previous works extended standard classification methods in the object detection task, mainly adopting the knowledge distillation framework. However, we argue that object detection introduces an additional problem, which has been overlooked. While objects belonging to new classes are learned thanks to their annotations, if no supervision is provided for other objects that may still be present in the input, the model learns to associate them to background regions. We propose to handle these missing annotations by revisiting the standard knowledge distillation framework. Our approach outperforms current state-of-the-art methods in every setting of the Pascal-VOC dataset. We further propose an extension to instance segmentation, outperforming the other baselines. Code can be found here: https://github.com/fcdl94/MMA

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation. Builds on 43 of its 62 references that are in the map. First posted on arXiv 19 Apr 2022.

Builds on

43 of 62 references.

References · 43

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2020End-to-End Object Detection with Transformerscited by 7,414
  4. 2017Mask R-CNNcited by 7,277
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  6. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  7. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  8. 2015Fast R-CNNcited by 2,933
  9. 2018YOLOv3: An Incremental Improvementcited by 2,659
  10. 2016Learning without Forgettingcited by 2,496
  11. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  12. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
31 more
  1. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  2. 2019Objects as Pointscited by 1,175
  3. 2017Continual Learning with Deep Generative Replaycited by 1,158
  4. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,105
  5. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  6. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 898
  7. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 742
  8. 2019Large Scale Incremental Learningcited by 732
  9. 2018End-to-End Incremental Learningcited by 597
  10. 2021DER: Dynamically Expandable Representation for Class Incremental Learningcited by 355
  11. 2021Towards Open World Object Detectioncited by 297
  12. 2021DyTox: Transformers for Continual Learning with DYnamic TOken eXpansioncited by 291
  13. 2018Learning without Memorizingcited by 250
  14. 2017Incremental Learning of Object Detectors without Catastrophic Forgettingcited by 208
  15. 2020Modeling the Background for Incremental Learning in Semantic Segmentationcited by 190
  16. 2019Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learningcited by 182
  17. 2020PLOP: Learning without Forgetting for Continual Semantic Segmentationcited by 177
  18. 2019Incremental Learning Techniques for Semantic Segmentationcited by 141
  19. 2021OW-DETR: Open-world Detection Transformercited by 129
  20. 2020Incremental Few-Shot Object Detectioncited by 102
  21. 2021Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representationscited by 96
  22. 2020Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNNcited by 61
  23. 2020Incremental Object Detection via Meta-Learningcited by 58
  24. 2020Online Continual Learning under Extreme Memory Constraintscited by 48
  25. 2021Incremental Learning in Semantic Segmentation from Image Labelscited by 39
  26. 2021Multi-View Correlation Distillation for Incremental Object Detectioncited by 36
  27. 2020RODEO: Replay for Online Object Detectioncited by 35
  28. 2020Lifelong Object Detectioncited by 25
  29. 2020Prototype-based Incremental Few-Shot Semantic Segmentationcited by 25
  30. 2021DIODE: Dilatable Incremental Object Detectioncited by 4
  31. 2022Modeling the Background for Incremental and Weakly-Supervised Semantic Segmentationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 5; 2024: 5; 2025: 6; 2026: 6.

23 papers.

Sort:

By area:

  1. 2023Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detectioncited by 32
  2. 2022CoMFormer: Continual Learning in Semantic and Panoptic Segmentationcited by 25
  3. 2024VLM-PL: Advanced Pseudo Labeling Approach for Class Incremental Object Detection via Vision-Language Modelcited by 23
  4. 2024Online Continual Learning For Interactive Instruction Following Agentscited by 22
  5. 2024ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuningcited by 20
  6. 2024Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object Detectioncited by 16
  7. 2025Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detectorcited by 6
  8. 2025CoMBO: Conflict Mitigation via Branched Optimization for Class Incremental Segmentationcited by 6
  9. 2023iPINNs: Incremental learning for Physics-informed neural networkscited by 3
  10. 2026Elastic Weight Consolidation Done Right for Continual Learningcited by 3
  11. 2023Class-Incremental Learning of Plant and Disease Detection: Growing Branches with Knowledge Distillationcited by 2
  12. 2023Dynamic Y-KD: A Hybrid Approach to Continual Instance Segmentationcited by 1
11 more
  1. 2023Tackling the Incomplete Annotation Issue in Universal Lesion Detection Task By Exploratory Trainingcited by 1
  2. 2025Teach YOLO to Remember: A Self-Distillation Approach for Continual Object Detectioncited by 1
  3. 2025DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmeticcited by 1
  4. 2026Learning on the Fly: Replay-Based Continual Object Perception for Indoor Dronescited by 1
  5. 2026EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformercited by 1
  6. 2026STAR-IOD: Scale-decoupled Topology Alignment with Pseudo-label Refinement for Remote Sensing Incremental Object Detectioncited by 1
  7. 2026Focus, Align, and Sustain: Counteracting Gradient Dilution in Incremental Object Detectioncited by 1
  8. 2024CASA: Class-Agnostic Shared Attributes in Vision-Language Models for Efficient Incremental Object Detectioncited by 0
  9. 2025Exploiting Stability-Plasticity Asymmetry in Pretrained Detectors for Incremental Object Detectioncited by 0
  10. 2025Parameterized Prompt for Incremental Object Detectioncited by 0
  11. 2026Beyond Prompt Degradation: Prototype-guided Dual-pool Prompting for Incremental Object Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Response-based Distillation for Incremental Object Detection
  2. 2021Revisiting Knowledge Distillation for Object Detection
  3. 2026Symbiosis-Inspired Knowledge Distillation for Incremental Object Detection
  4. 2021Class-Incremental Few-Shot Object Detection
  5. 2024Task Integration Distillation for Object Detectors
  6. 2022Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation
  7. 2025Architectural Insights into Knowledge Distillation for Object Detection: A Comprehensive Review
  8. 2021Distilling Image Classifiers in Object Detectors