Latent Replay Detection: Memory-Efficient Continual Object Detection on Microcontrollers via Task-Adaptive Compression

• URL: http://arxiv.org/abs/2603.00138v1
• Date: Tue, 24 Feb 2026 07:35:27 GMT
• Title: Latent Replay Detection: Memory-Efficient Continual Object Detection on Microcontrollers via Task-Adaptive Compression
• Abstract summary: Existing continual learning methods require storing raw images far exceeding MCU memory budgets.<n>We present Latent Replay Detection (LRD), the first framework for continual object detection under MCU memory constraints.<n> Deployed on STM32H753ZI, ESP32-S3, and MAX78000 MCUs, LRD achieves 4.9-97.5ms latency per inference within a 64KB memory budget.
• Score: 0.14504054468850666
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• MAUPITI: On-Device Prototype-Based Learning on a Smart Infrared Sensor [4.173901102591031]
  Low-resolution infrared (IR) array sensors represent an interesting solution for privacy-preserving human sensing in embedded systems.<n>We describe a smart multi-pixel IR sensor integrating a 16$times$16 thermal (TMOS) array and a RISC-V microcontroller extended with low-precision SIMD instructions.
  arXiv  Detail & Related papers  (2026-08-07T13:07:24Z)
• UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams [77.52140119830241]
  We propose UniMem, a self-routing framework for autonomous memory management.<n>UniMem uses learnable routing tokens as memory controllers, enabling adaptive coordination between complementary memory pathways.<n>Experiments on long-horizon streaming task sequences show that UniMem consistently outperforms baselines while maintaining execution fidelity.
  arXiv  Detail & Related papers  (2026-07-28T17:28:21Z)
• AHC: Meta-Learned Adaptive Compression for Continual Object Detection on Memory-Constrained Microcontrollers [0.14504054468850666]
  Continual object detection on microcontrollers (MCUs) with under 100KB memory requires efficient feature compression.<n>We introduce Adaptive Hierarchical Compression (AHC), a meta-learning framework featuring three key innovations.<n>AHC enables practical continual detection within a 100KB replay budget, achieving competitive accuracy through mean-pooled compressed feature replay.
  arXiv  Detail & Related papers  (2026-02-24T07:06:51Z)
• TinyVLM: Zero-Shot Object Detection on Microcontrollers via Vision-Language Distillation with Matryoshka Embeddings [0.14504054468850666]
  We present TinyVLM, the first framework enabling zero-shot object detection on resource-constrained MCUs with less than 1MB of memory.<n>TinyVLM achieves competitive zero-shot accuracy on COCO, Flowers102, and Food101 while requiring only 285KB of RAM and 892KB of flash memory.
  arXiv  Detail & Related papers  (2026-02-24T05:32:51Z)
• PRISM: Performer RS-IMLE for Single-pass Multisensory Imitation Learning [51.24484551729328]
  We introduce PRISM, a single-pass policy based on a batch-global rejection-sampling variant of IMLE.<n> PRISM couples a temporal multisensory encoder with a linear-attention generator using a Performer architecture.<n>We demonstrate the efficacy of PRISM on a diverse real-world hardware suite, including loco-manipulation using a Unitree Go2 with a 7-DoF arm D1 and tabletop manipulation with a UR5 manipulator.
  arXiv  Detail & Related papers  (2026-02-02T17:57:37Z)
• EdgeFlex-Transformer: Transformer Inference for Edge Devices [2.1130318406254074]
  We propose a lightweight yet effective multi-stage optimization pipeline designed to compress and accelerate Vision Transformers (ViTs)<n>Our methodology combines activation profiling, memory-aware pruning, selective mixed-precision execution, and activation-aware quantization (AWQ) to reduce the model's memory footprint without requiring costly retraining or task-specific fine-tuning.<n>Experiments on CIFAR-10 demonstrate that the fully optimized model achieves a 76% reduction in peak memory usage and over 6x lower latency, while retaining or even improving accuracy compared to the original FP32 baseline.
  arXiv  Detail & Related papers  (2025-12-17T21:45:12Z)
• MSSDF: Modality-Shared Self-supervised Distillation for High-Resolution Multi-modal Remote Sensing Image Learning [25.381211868583826]
  We propose a multi-modal self-supervised learning framework that leverages high-resolution RGB images, multi-spectral data, and digital surface models (DSM) for pre-training.<n>We evaluate the proposed method on multiple downstream tasks, covering typical remote sensing applications such as scene classification, semantic segmentation, change detection, object detection, and depth estimation.
  arXiv  Detail & Related papers  (2025-06-11T02:01:36Z)
• CS-Net:Contribution-based Sampling Network for Point Cloud Simplification [50.55658910053004]
  Point cloud sampling plays a crucial role in reducing computation costs and storage requirements for various vision tasks.<n>Traditional sampling methods, such as farthest point sampling, lack task-specific information.<n>We propose a contribution-based sampling network (CS-Net), where the sampling operation is formulated as a Top-k operation.
  arXiv  Detail & Related papers  (2025-01-18T14:56:09Z)
• MutDet: Mutually Optimizing Pre-training for Remote Sensing Object Detection [36.478530086163744]
  We propose a novel Mutually optimizing pre-training framework for remote sensing object Detection, dubbed as MutDet. MutDet fuses the object embeddings and detector features bidirectionally in the last encoder layer, enhancing their information interaction. Experiments on various settings show new state-of-the-art transfer performance.
  arXiv  Detail & Related papers  (2024-07-13T15:28:15Z)
• MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memory [76.02294791513552]
  We propose a hardware-algorithm co-optimizations method called MCUFormer to deploy vision transformers on microcontrollers with extremely limited memory. Experimental results demonstrate that our MCUFormer achieves 73.62% top-1 accuracy on ImageNet for image classification with 320KB memory.
  arXiv  Detail & Related papers  (2023-10-25T18:00:26Z)
• Recurrent Vision Transformers for Object Detection with Event Cameras [62.27246562304705]
  We present Recurrent Vision Transformers (RVTs), a novel backbone for object detection with event cameras. RVTs can be trained from scratch to reach state-of-the-art performance on event-based object detection. Our study brings new insights into effective design choices that can be fruitful for research beyond event-based vision.
  arXiv  Detail & Related papers  (2022-12-11T20:28:59Z)
• MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning [72.80896338009579]
  We find that the memory bottleneck is due to the imbalanced memory distribution in convolutional neural network (CNN) designs. We propose a generic patch-by-patch inference scheduling, which significantly cuts down the peak memory. We automate the process with neural architecture search to jointly optimize the neural architecture and inference scheduling, leading to MCUNetV2.
  arXiv  Detail & Related papers  (2021-10-28T17:58:45Z)
• A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays [66.62377866022221]
  Latent Replay-based Continual Learning (CL) techniques enable online, serverless adaptation in principle. We introduce a HW/SW platform for end-to-end CL based on a 10-core FP32-enabled parallel ultra-low-power processor. Our results show that by combining these techniques, continual learning can be achieved in practice using less than 64MB of memory.
  arXiv  Detail & Related papers  (2021-10-20T11:01:23Z)
• A Variational Information Bottleneck Based Method to Compress Sequential Networks for Human Action Recognition [9.414818018857316]
  We propose a method to effectively compress Recurrent Neural Networks (RNNs) used for Human Action Recognition (HAR) We use a Variational Information Bottleneck (VIB) theory-based pruning approach to limit the information flow through the sequential cells of RNNs to a small subset. We combine our pruning method with a specific group-lasso regularization technique that significantly improves compression. It is shown that our method achieves over 70 times greater compression than the nearest competitor with comparable accuracy for the task of action recognition on UCF11.
  arXiv  Detail & Related papers  (2020-10-03T12:41:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.