# Teach YOLO to Remember: A Self-Distillation Approach for Continual Object Detection

arXiv: https://arxiv.org/abs/2503.04688 · HTML: https://mlsanity.com/paper/2503.04688/

## Key facts

- Cited by 1 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 21 of its 25 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 21 of 21)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection](https://mlsanity.com/paper/2006.04388/) (2020)
- [TOOD: Task-aligned One-stage Object Detection](https://mlsanity.com/paper/2108.07755/) (2021)
- [Incremental Learning of Object Detectors without Catastrophic Forgetting](https://mlsanity.com/paper/1708.06977/) (2017)
- [Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation](https://mlsanity.com/paper/2105.08919/) (2021)
- [Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation](https://mlsanity.com/paper/2005.03572/) (2020)
- [Anomaly Detection in Autonomous Driving: A Survey](https://mlsanity.com/paper/2204.07974/) (2022)
- [Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation](https://mlsanity.com/paper/2204.02136/) (2022)
- [Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNN](https://mlsanity.com/paper/2003.03901/) (2020)
- [SID: Incremental Learning for Anchor-Free Object Detection via Selective and Inter-Related Distillation](https://mlsanity.com/paper/2012.15439/) (2020)
- [Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection](https://mlsanity.com/paper/2307.12427/) (2023)
- [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)
- [Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object Detection](https://mlsanity.com/paper/2407.11499/) (2024)
- [Replay Consolidation with Label Propagation for Continual Object Detection](https://mlsanity.com/paper/2409.05650/) (2024)

## Built on by (most cited first, 1 of 1)

- [Towards Field-Ready AI-based Malaria Diagnosis: A Continual Learning Approach](https://mlsanity.com/paper/2507.23648/) (2025)

## Abstract (arXiv)

Real-time object detectors like YOLO achieve exceptional performance when trained on large datasets for multiple epochs. However, in real-world scenarios where data arrives incrementally, neural networks suffer from catastrophic forgetting, leading to a loss of previously learned knowledge. To address this, prior research has explored strategies for Class Incremental Learning (CIL) in Continual Learning for Object Detection (CLOD), with most approaches focusing on two-stage object detectors. However, existing work suggests that Learning without Forgetting (LwF) may be ineffective for one-stage anchor-free detectors like YOLO due to noisy regression outputs, which risk transferring corrupted knowledge. In this work, we introduce YOLO LwF, a self-distillation approach tailored for YOLO-based continual object detection. We demonstrate that when coupled with a replay memory, YOLO LwF significantly mitigates forgetting. Compared to previous approaches, it achieves state-of-the-art performance, improving mAP by +2.1% and +2.9% on the VOC and COCO benchmarks, respectively.