# Latent Distillation for Continual Object Detection at the Edge

arXiv: https://arxiv.org/abs/2409.01872 · HTML: https://mlsanity.com/paper/2409.01872/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 52 references that are in the map.
- First posted on arXiv 3 Sep 2024.

## Builds on (most cited first, 24 of 24)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection](https://mlsanity.com/paper/2006.04388/) (2020)
- [Online Continual Learning in Image Classification: An Empirical Survey](https://mlsanity.com/paper/2101.10423/) (2021)
- [Incremental Learning of Object Detectors without Catastrophic Forgetting](https://mlsanity.com/paper/1708.06977/) (2017)
- [FCOS: A simple and strong anchor-free object detector](https://mlsanity.com/paper/2006.09214/) (2020)
- [A Survey of Modern Deep Learning based Object Detection Models](https://mlsanity.com/paper/2104.11892/) (2021)
- [Latent Replay for Real-Time Continual Learning](https://mlsanity.com/paper/1912.01100/) (2019)
- [Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNN](https://mlsanity.com/paper/2003.03901/) (2020)
- [SpaceNet: Make Free Space For Continual Learning](https://mlsanity.com/paper/2007.07617/) (2020)
- [A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays](https://mlsanity.com/paper/2110.10486/) (2021)
- [RODEO: Replay for Online Object Detection](https://mlsanity.com/paper/2008.06439/) (2020)
- [SID: Incremental Learning for Anchor-Free Object Detection via Selective and Inter-Related Distillation](https://mlsanity.com/paper/2012.15439/) (2020)
- [Lifelong Object Detection](https://mlsanity.com/paper/2009.01129/) (2020)
- [Continual Object Detection: A review of definitions, strategies, and challenges](https://mlsanity.com/paper/2205.15445/) (2022)
- [Tiny Robot Learning: Challenges and Directions for Machine Learning in Resource-Constrained Robots](https://mlsanity.com/paper/2205.05748/) (2022)
- [PhiNets: a scalable backbone for low-power AI at the edge](https://mlsanity.com/paper/2110.00337/) (2021)
- [Continual Learning Approaches for Anomaly Detection](https://mlsanity.com/paper/2212.11192/) (2022)

## Built on by (most cited first, 4 of 4)

- [Replay Consolidation with Label Propagation for Continual Object Detection](https://mlsanity.com/paper/2409.05650/) (2024)
- [MicroFlow: An Efficient Rust-Based Inference Engine for TinyML](https://mlsanity.com/paper/2409.19432/) (2024)
- [TiROD: Tiny Robotics Dataset and Benchmark for Continual Object Detection](https://mlsanity.com/paper/2409.16215/) (2024)
- [Architectural Insights into Knowledge Distillation for Object Detection: A Comprehensive Review](https://mlsanity.com/paper/2508.03317/) (2025)

## Abstract (arXiv)

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.