AHC: Meta-Learned Adaptive Compression for Continual Object Detection on Memory-Constrained Microcontrollers

TL;DR

This paper introduces AHC, a meta-learned adaptive compression framework for continual object detection on memory-limited microcontrollers, enabling efficient, task-adaptive feature compression with formal guarantees.

Contribution

It presents a novel MAML-based hierarchical compression method with dual-memory architecture, tailored for continual detection under strict memory constraints.

Findings

Achieves competitive detection accuracy within 100KB memory budget.

Effectively adapts to new tasks with only 5 gradient steps per task.

Provides theoretical bounds on catastrophic forgetting related to compression error and memory.

Abstract

Deploying continual object detection on microcontrollers (MCUs) with under 100KB memory requires efficient feature compression that can adapt to evolving task distributions. Existing approaches rely on fixed compression strategies (e.g., FiLM conditioning) that cannot adapt to heterogeneous task characteristics, leading to suboptimal memory utilization and catastrophic forgetting. We introduce Adaptive Hierarchical Compression (AHC), a meta-learning framework featuring three key innovations: (1) true MAML-based compression that adapts via gradient descent to each new task in just 5 inner-loop steps, (2) hierarchical multi-scale compression with scale-aware ratios (8:1 for P3, 6.4:1 for P4, 4:1 for P5) matching FPN redundancy patterns, and (3) a dual-memory architecture combining short-term and long-term banks with importance-based consolidation under a hard 100KB budget. We provide formal theoretical guarantees bounding catastrophic forgetting as O({\epsilon}{sq.root(T)} + 1/{sq.root(M)}) where {\epsilon} is compression error, T is task count, and M is memory size. Experiments on CORe50, TiROD, and PASCAL VOC benchmarks with three standard baselines (Fine-tuning,EWC, iCaRL) demonstrate that AHC enables practical continual detection within a 100KB replay budget, achieving competitive accuracy through mean-pooled compressed feature replay combined with EWC regularization and feature distillation.