mlsanityData to 7 Oct 2026

RODEO: Replay for Online Object Detection

arXiv 2008.06439 ↗First posted 14 Aug 2020cs.CV cs.LGcited by 35

Not on the map. Why?

Abstract (arXiv)

Humans can incrementally learn to do new visual detection tasks, which is a huge challenge for today's computer vision systems. Incrementally trained deep learning models lack backwards transfer to previously seen classes and suffer from a phenomenon known as "catastrophic forgetting." In this paper, we pioneer online streaming learning for object detection, where an agent must learn examples one at a time with severe memory and computational constraints. In object detection, a system must output all bounding boxes for an image with the correct label. Unlike earlier work, the system described in this paper can learn this task in an online manner with new classes being introduced over time. We achieve this capability by using a novel memory replay mechanism that efficiently replays entire scenes. We achieve state-of-the-art results on both the PASCAL VOC 2007 and MS COCO datasets.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 8; 2023: 7; 2024: 7; 2025: 3; 2026: 2.

35 papers.

Sort:

By area:

  1. 2021Towards Open World Object Detectioncited by 297
  2. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 242
  3. 2021Replay in Deep Learning: Current Approaches and Missing Biological Elementscited by 71
  4. 2022An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditionscited by 54
  5. 2021Self-Supervised Training Enhances Online Continual Learningcited by 53
  6. 2024SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detectioncited by 42
  7. 2023Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detectioncited by 32
  8. 2022Continual Object Detection: A review of definitions, strategies, and challengescited by 25
  9. 2023SIESTA: Efficient Online Continual Learning with Sleepcited by 24
  10. 2022Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detectioncited by 23
  11. 2022Modeling Missing Annotations for Incremental Learning in Object Detectioncited by 23
  12. 2024VLM-PL: Advanced Pseudo Labeling Approach for Class Incremental Object Detection via Vision-Language Modelcited by 23
23 more
  1. 2024Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object Detectioncited by 16
  2. 2023Overcoming the Stability Gap in Continual Learningcited by 13
  3. 2023GRASP: A Rehearsal Policy for Efficient Online Continual Learningcited by 13
  4. 2024Object Detectors in the Open Environment: Challenges, Solutions, and Outlookcited by 13
  5. 2024Open World Object Detection: A Surveycited by 13
  6. 2021Selective Replay Enhances Learning in Online Continual Analogical Reasoningcited by 12
  7. 2022Improving Replay-Based Continual Semantic Segmentation with Smart Data Selectioncited by 8
  8. 2022Re-examining Distillation For Continual Object Detectioncited by 5
  9. 2023Class-Wise Buffer Management for Incremental Object Detection: An Effective Buffer Training Strategycited by 5
  10. 2025Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detectorcited by 5
  11. 2024Latent Distillation for Continual Object Detection at the Edgecited by 4
  12. 2022Cold Start Streaming Learning for Deep Networkscited by 3
  13. 20223rd Continual Learning Workshop Challenge on Egocentric Category and Instance Level Object Understandingcited by 3
  14. 2021Exploiting latent representation of sparse semantic layers for improved short-term motion prediction with Capsule Networkscited by 2
  15. 2024TiROD: Tiny Robotics Dataset and Benchmark for Continual Object Detectioncited by 2
  16. 20212nd Place Solution for SODA10M Challenge 2021 -- Continual Detection Trackcited by 1
  17. 2021Reviewing continual learning from the perspective of human-level intelligencecited by 1
  18. 2023MultIOD: Rehearsal-free Multihead Incremental Object Detectorcited by 1
  19. 2025A Good Start Matters: Enhancing Continual Learning with Data-Driven Weight Initializationcited by 1
  20. 2025DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmeticcited by 1
  21. 2026EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformercited by 1
  22. 2026STAR-IOD: Scale-decoupled Topology Alignment with Pseudo-label Refinement for Remote Sensing Incremental Object Detectioncited by 1
  23. 2023CSSL-MHTR: Continual Self-Supervised Learning for Scalable Multi-script Handwritten Text Recognitioncited by 0