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

arXiv: https://arxiv.org/abs/2603.00138 · HTML: https://mlsanity.com/paper/2603.00138/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 24 Feb 2026.

## Builds on (most cited first, 22 of 22)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [CORe50: a New Dataset and Benchmark for Continuous Object Recognition](https://mlsanity.com/paper/1705.03550/) (2017)
- [MCUNet: Tiny Deep Learning on IoT Devices](https://mlsanity.com/paper/2007.10319/) (2020)
- [Rainbow Memory: Continual Learning with a Memory of Diverse Samples](https://mlsanity.com/paper/2103.17230/) (2021)
- [FOSTER: Feature Boosting and Compression for Class-Incremental Learning](https://mlsanity.com/paper/2204.04662/) (2022)
- [REMIND Your Neural Network to Prevent Catastrophic Forgetting](https://mlsanity.com/paper/1910.02509/) (2019)
- [Meta-Learning Representations for Continual Learning](https://mlsanity.com/paper/1905.12588/) (2019)
- [Online Meta-Learning](https://mlsanity.com/paper/1902.08438/) (2019)
- [Continual Learning via Neural Pruning](https://mlsanity.com/paper/1903.04476/) (2019)
- [TinyOL: TinyML with Online-Learning on Microcontrollers](https://mlsanity.com/paper/2103.08295/) (2021)
- [Continual Detection Transformer for Incremental Object Detection](https://mlsanity.com/paper/2304.03110/) (2023)
- [La-MAML: Look-ahead Meta Learning for Continual Learning](https://mlsanity.com/paper/2007.13904/) (2020)
- [DSORT-MCU: Detecting Small Objects in Real-Time on Microcontroller Units](https://mlsanity.com/paper/2410.16769/) (2024)

## Abstract (arXiv)

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.