教YOLO记忆：一种用于持续目标检测的自蒸馏方法
Teach YOLO to Remember: A Self-Distillation Approach for Continual Object Detection
AI总结：
针对YOLO等单阶段无锚框检测器在持续目标检测中的灾难性遗忘问题，提出YOLO LwF自蒸馏方法，结合重放记忆显著缓解遗忘，在VOC和COCO基准上分别提升mAP +2.1%和+2.9%，达到最先进性能。
摘要：
像YOLO这样的实时目标检测器在大型数据集上训练多个epoch时能取得卓越性能。然而，在数据增量到达的真实场景中，神经网络会遭受灾难性遗忘，导致先前学习的知识丢失。为解决此问题，先前研究探索了目标检测持续学习（CLOD）中的类别增量学习（CIL）策略，且大多方法集中于两阶段目标检测器。然而，现有工作表明，对于像YOLO这样的单阶段无锚框检测器，由于存在噪声回归输出，无遗忘学习（LwF）可能无效，这有传递损坏知识的风险。在本研究中，我们引入了YOLO LwF，一种专为基于YOLO的持续目标检测定制的自蒸馏方法。我们证明，当与重放记忆结合使用时，YOLO LwF能显著缓解遗忘。与先前方法相比，它实现了最先进的性能，在VOC和COCO基准上分别将mAP提高了+2.1%和+2.9%。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
