轻量级检测器+新蒸馏方法，让边缘设备持续学习目标检测更高效。
Latent Distillation for Continual Object Detection at the Edge
- 用NanoDet轻量检测器适配边缘设备的持续学习场景
- 提出潜空间蒸馏（LD）方法，降低74%参数开销和56%计算量
- 适合资源受限的自动驾驶、机器人等实时目标检测应用
尽管现有目标检测方法性能卓越，但应对数据分布漂移仍是挑战。持续学习（CL）可帮助模型适应新数据的同时保持旧任务性能，尤其适用于汽车与机器人等动态环境中的边缘设备。本文针对边缘设备在持续目标检测（CLOD）中的内存与计算约束问题，首先评估了开源、轻量且快速的检测器NanoDet在该场景下的适用性，优于文献中常用的大型架构；其次提出一种新型持续学习方法——潜空间蒸馏（Latent Distillation, LD），显著减少当前最优蒸馏方法所需的运算量与内存开销，同时几乎不损失检测性能。实验基于VOC和COCO基准验证，相较其他蒸馏方法，每轮模型更新可降低74%的蒸馏参数开销和56%的浮点运算量（FLOPs）。
原文摘要 · Abstract (English)
While numerous methods achieving remarkable performance exist in the Object Detection literature, addressing data distribution shifts remains challenging. Continual Learning (CL) offers solutions to this issue, enabling models to adapt to new data while maintaining performance on previous data. This is particularly pertinent for edge devices, common in dynamic environments like automotive and robotics. In this work, we address the memory and computation constraints of edge devices in the Continual Learning for Object Detection (CLOD) scenario. Specifically, (i) we investigate the suitability of an open-source, lightweight, and fast detector, namely NanoDet, for CLOD on edge devices, improving upon larger architectures used in the literature. Moreover, (ii) we propose a novel CL method, called Latent Distillation~(LD), that reduces the number of operations and the memory required by state-of-the-art CL approaches without significantly compromising detection performance. Our approach is validated using the well-known VOC and COCO benchmarks, reducing the distillation parameter overhead by 74\% and the Floating Points Operations~(FLOPs) by 56\% per model update compared to other distillation methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。