mlsanityData to 7 Oct 2026

Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection

arXiv 2307.12427 ↗First posted 23 Jul 2023cs.CV cs.LGcited by 32

Not on the map. Why?

Abstract (arXiv)

In incremental learning, replaying stored samples from previous tasks together with current task samples is one of the most efficient approaches to address catastrophic forgetting. However, unlike incremental classification, image replay has not been successfully applied to incremental object detection (IOD). In this paper, we identify the overlooked problem of foreground shift as the main reason for this. Foreground shift only occurs when replaying images of previous tasks and refers to the fact that their background might contain foreground objects of the current task. To overcome this problem, a novel and efficient Augmented Box Replay (ABR) method is developed that only stores and replays foreground objects and thereby circumvents the foreground shift problem. In addition, we propose an innovative Attentive RoI Distillation loss that uses spatial attention from region-of-interest (RoI) features to constrain current model to focus on the most important information from old model. ABR significantly reduces forgetting of previous classes while maintaining high plasticity in current classes. Moreover, it considerably reduces the storage requirements when compared to standard image replay. Comprehensive experiments on Pascal-VOC and COCO datasets support the state-of-the-art performance of our model.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 48 of its 68 references that are in the map. First posted on arXiv 23 Jul 2023.

Builds on

48 of 68 references.

References · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2017Mask R-CNNcited by 7,259
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  9. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  10. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  11. 2015Fast R-CNNcited by 2,930
  12. 2018YOLOv3: An Incremental Improvementcited by 2,652
36 more
  1. 2016Learning without Forgettingcited by 2,465
  2. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  3. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  4. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  5. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  6. 2017Continual Learning with Deep Generative Replaycited by 1,152
  7. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,094
  8. 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,059
  9. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  10. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 882
  11. 2017Focal Loss for Dense Object Detectioncited by 749
  12. 2017Lifelong Learning with Dynamically Expandable Networkscited by 689
  13. 2018End-to-End Incremental Learningcited by 596
  14. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  15. 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 446
  16. 2021Towards Open World Object Detectioncited by 297
  17. 2021DyTox: Transformers for Continual Learning with DYnamic TOken eXpansioncited by 291
  18. 2018Learning without Memorizingcited by 249
  19. 2020Semantic Drift Compensation for Class-Incremental Learningcited by 241
  20. 2017Incremental Learning of Object Detectors without Catastrophic Forgettingcited by 208
  21. 2020Modeling the Background for Incremental Learning in Semantic Segmentationcited by 189
  22. 2017FearNet: Brain-Inspired Model for Incremental Learningcited by 177
  23. 2020PLOP: Learning without Forgetting for Continual Semantic Segmentationcited by 177
  24. 2021OW-DETR: Open-world Detection Transformercited by 129
  25. 2022Representation Compensation Networks for Continual Semantic Segmentationcited by 72
  26. 2022Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillationcited by 72
  27. 2020Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNNcited by 61
  28. 2023Continual Detection Transformer for Incremental Object Detectioncited by 59
  29. 2020Incremental Object Detection via Meta-Learningcited by 58
  30. 2021Multi-View Correlation Distillation for Incremental Object Detectioncited by 36
  31. 2020RODEO: Replay for Online Object Detectioncited by 35
  32. 2020Lifelong Object Detectioncited by 25
  33. 2022Modeling Missing Annotations for Incremental Learning in Object Detectioncited by 23
  34. 2022Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentationcited by 21
  35. 2022Re-examining Distillation For Continual Object Detectioncited by 5
  36. 2021DIODE: Dilatable Incremental Object Detectioncited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 12; 2025: 10; 2026: 9.

32 papers.

Sort:

By area:

  1. 2023FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learningcited by 86
  2. 2024Resurrecting Old Classes with New Data for Exemplar-Free Continual Learningcited by 33
  3. 2024VLM-PL: Advanced Pseudo Labeling Approach for Class Incremental Object Detection via Vision-Language Modelcited by 23
  4. 2024Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object Detectioncited by 16
  5. 2025Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgettingcited by 16
  6. 2024Is Parameter Collision Hindering Continual Learning in LLMs?cited by 15
  7. 2024Object Detectors in the Open Environment: Challenges, Solutions, and Outlookcited by 13
  8. 2024Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformerscited by 9
  9. 2024Preventing Catastrophic Forgetting through Memory Networks in Continuous Detectioncited by 7
  10. 2024Multi-Label Continual Learning for the Medical Domain: A Novel Benchmarkcited by 6
  11. 2024Replay Consolidation with Label Propagation for Continual Object Detectioncited by 6
  12. 2025Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detectorcited by 5
20 more
  1. 2025RICO: Two Realistic Benchmarks and an In-Depth Analysis for Incremental Learning in Object Detectioncited by 5
  2. 2024Reconstruct before Query: Continual Missing Modality Learning with Decomposed Prompt Collaborationcited by 4
  3. 2026CGL: Advancing Continual GUI Learning via Reinforcement Fine-Tuningcited by 3
  4. 2024IOR: Inversed Objects Replay for Incremental Object Detectioncited by 2
  5. 2025Incremental Object Detection with Prompt-based Methodscited by 2
  6. 2025Teach YOLO to Remember: A Self-Distillation Approach for Continual Object Detectioncited by 1
  7. 2025DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmeticcited by 1
  8. 2025OW-CLIP: Data-Efficient Visual Supervision for Open-World Object Detection via Human-AI Collaborationcited by 1
  9. 2026Learning on the Fly: Replay-Based Continual Object Perception for Indoor Dronescited by 1
  10. 2026EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformercited by 1
  11. 2026STAR-IOD: Scale-decoupled Topology Alignment with Pseudo-label Refinement for Remote Sensing Incremental Object Detectioncited by 1
  12. 2026Focus, Align, and Sustain: Counteracting Gradient Dilution in Incremental Object Detectioncited by 1
  13. 2026Symbiosis-Inspired Knowledge Distillation for Incremental Object Detectioncited by 1
  14. 2024CASA: Class-Agnostic Shared Attributes in Vision-Language Models for Efficient Incremental Object Detectioncited by 0
  15. 2025Exploiting Stability-Plasticity Asymmetry in Pretrained Detectors for Incremental Object Detectioncited by 0
  16. 2025Incremental Human-Object Interaction Detection with Invariant Relation Representation Learningcited by 0
  17. 2025Parameterized Prompt for Incremental Object Detectioncited by 0
  18. 2026Better Matching, Less Forgetting: A Quality-Guided Matcher for Transformer-based Incremental Object Detectioncited by 0
  19. 2026Beyond Prompt Degradation: Prototype-guided Dual-pool Prompting for Incremental Object Detectioncited by 0
  20. 2026Breaking the Model Forgetting Cycle in Long-Incremental 3D Object Detectioncited by 0