在微控制器上实现持续学习的物体检测，内存占用仅150字节/样本。
Latent Replay Detection: Memory-Efficient Continual Object Detection on Microcontrollers via Task-Adaptive Compression
- 用可学习的FiLM压缩机制，按任务自适应保留关键特征。
- 通过最大化边界框多样性选择样例，避免定位偏差。
- 支持在64KB内存下部署，适合资源受限的边缘设备。
将目标检测部署到微控制器（MCU）可实现智能边缘设备，但现有模型无法在部署后学习新类别。当前持续学习方法需存储原始图像，远超MCU数十千字节的内存限制。本文提出首个满足MCU内存约束的持续目标检测框架——隐空间重放检测（LRD）。核心贡献包括：1. 任务自适应压缩：不同于固定PCA，采用带FiLM（特征逐通道线性调制）条件的可学习压缩，任务特定嵌入调节压缩过程，以保留各任务分布下的判别特征；2. 空间多样样例选择：传统采样忽略空间信息，本文在交并比（IoU）空间中采用最远点采样，最大化边界框多样性，防止重放中的定位偏差；3. 可部署于MCU的系统设计：隐空间重放仅需每样本150字节，相比图像超过10KB，使64KB缓冲区可容纳400+样例。在CORe50数据集（50类，5任务）上的实验表明，LRD在初始任务上保持mAP@50，后续任务性能稳定，显著优于简单微调，且严格满足MCU约束。任务自适应的FiLM压缩与空间多样采样协同工作，有效维持检测能力。在STM32H753ZI、ESP32-S3和MAX78000 MCU上部署，单次推理延迟为4.9–97.5毫秒，内存占用64KB，首次实现边缘设备上实用的持续检测。
原文摘要 · Abstract (English)
Deploying object detection on microcontrollers (MCUs) enables intelligent edge devices but current models cannot learn new object categories after deployment. Existing continual learning methods require storing raw images far exceeding MCU memory budgets of tens of kilobytes. We present Latent Replay Detection (LRD), the first framework for continual object detection under MCU memory constraints. Our key contributions are: 1. Task-Adaptive Compression: Unlike fixed PCA, we propose learnable compression with FiLM (Feature-wise Linear Modulation) conditioning, where task specific embeddings modulate the compression to preserve discriminative features for each task's distribution; 2. Spatial-Diverse Exemplar Selection: Traditional sampling ignores spatial information critical for detection - we select exemplars maximizing bounding box diversity via farthest-point sampling in IoU space, preventing localization bias in replay; 3. MCU-Deployable System: Our latent replay stores 150 bytes per sample versus >10KB for images, enabling a 64KB buffer to hold 400+ exemplars. Experiments on CORe50 (50 classes, 5 tasks) demonstrate that LRD achieves mAP@50 on the initial task and maintains strong performance across subsequent tasks - a significant improvement over naive fine-tuning while operating within strict MCU constraints. Our task-adaptive FiLM compression and spatial diverse exemplar selection work synergistically to preserve detection capabilities. Deployed on STM32H753ZI, ESP32-S3, and MAX78000 MCUs, LRD achieves 4.9-97.5ms latency per inference within a 64KB memory budget-enabling practical continual detection on edge devices for the first time.
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。