# Lifelong Object Detection

arXiv: https://arxiv.org/abs/2009.01129 · HTML: https://mlsanity.com/paper/2009.01129/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Sep 2020.

## Built on by (most cited first, 25 of 25)

- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Continual Detection Transformer for Incremental Object Detection](https://mlsanity.com/paper/2304.03110/) (2023)
- [Wanderlust: Online Continual Object Detection in the Real World](https://mlsanity.com/paper/2108.11005/) (2021)
- [Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection](https://mlsanity.com/paper/2307.12427/) (2023)
- [Continual Semi-Supervised Learning through Contrastive Interpolation Consistency](https://mlsanity.com/paper/2108.06552/) (2021)
- [Continual Object Detection: A review of definitions, strategies, and challenges](https://mlsanity.com/paper/2205.15445/) (2022)
- [Modeling Missing Annotations for Incremental Learning in Object Detection](https://mlsanity.com/paper/2204.08766/) (2022)
- [VLM-PL: Advanced Pseudo Labeling Approach for Class Incremental Object Detection via Vision-Language Model](https://mlsanity.com/paper/2403.05346/) (2024)
- [Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism](https://mlsanity.com/paper/2205.03055/) (2022)
- [Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object Detection](https://mlsanity.com/paper/2407.11499/) (2024)
- [Bridging Non Co-occurrence with Unlabeled In-the-wild Data for Incremental Object Detection](https://mlsanity.com/paper/2110.15017/) (2021)
- [Object Detectors in the Open Environment: Challenges, Solutions, and Outlook](https://mlsanity.com/paper/2403.16271/) (2024)
- [NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forging](https://mlsanity.com/paper/2303.04958/) (2023)
- [Online Unsupervised Domain Adaptation for Person Re-identification](https://mlsanity.com/paper/2205.04383/) (2022)
- [DCA: Dividing and Conquering Amnesia in Incremental Object Detection](https://mlsanity.com/paper/2503.15295/) (2025)
- [Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detection](https://mlsanity.com/paper/2212.10147/) (2022)
- [Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector](https://mlsanity.com/paper/2502.05540/) (2025)
- [Re-examining Distillation For Continual Object Detection](https://mlsanity.com/paper/2204.01407/) (2022)
- [Saliency-Guided Hidden Associative Replay for Continual Learning](https://mlsanity.com/paper/2310.04334/) (2023)
- [COOLer: Class-Incremental Learning for Appearance-Based Multiple Object Tracking](https://mlsanity.com/paper/2310.03006/) (2023)
- [Latent Distillation for Continual Object Detection at the Edge](https://mlsanity.com/paper/2409.01872/) (2024)
- [Source-Guided Similarity Preservation for Online Person Re-Identification](https://mlsanity.com/paper/2402.15206/) (2024)
- [Saliency-Augmented Memory Completion for Continual Learning](https://mlsanity.com/paper/2212.13242/) (2022)
- [MultIOD: Rehearsal-free Multihead Incremental Object Detector](https://mlsanity.com/paper/2309.05334/) (2023)
- [Hierarchical Neural Collapse Detection Transformer for Class Incremental Object Detection](https://mlsanity.com/paper/2506.08562/) (2025)

## Abstract (arXiv)

Recent advances in object detection have benefited significantly from rapid developments in deep neural networks. However, neural networks suffer from the well-known issue of catastrophic forgetting, which makes continual or lifelong learning problematic. In this paper, we leverage the fact that new training classes arrive in a sequential manner and incrementally refine the model so that it additionally detects new object classes in the absence of previous training data. Specifically, we consider the representative object detector, Faster R-CNN, for both accurate and efficient prediction. To prevent abrupt performance degradation due to catastrophic forgetting, we propose to apply knowledge distillation on both the region proposal network and the region classification network, to retain the detection of previously trained classes. A pseudo-positive-aware sampling strategy is also introduced for distillation sample selection. We evaluate the proposed method on PASCAL VOC 2007 and MS COCO benchmarks and show competitive mAP and 6x inference speed improvement, which makes the approach more suitable for real-time applications. Our implementation will be publicly available.