Deep Microcompression: Structured Pruning and Bit-packed Quantization for Microcontrollers

• URL: http://arxiv.org/abs/2609.05081v1
• Date: Fri, 04 Sep 2026 12:38:07 GMT
• Title: Deep Microcompression: Structured Pruning and Bit-packed Quantization for Microcontrollers
• Abstract summary: This paper introduces Deep Microcompression (DMC), a hardware-aware pipeline for deep learning inference on bare-metal microcontrollers.<n>DMC integrates structured pruning, quantization-aware training, and fixed-length bit-packing to achieve a 55.8times weight compression ratio on LeNet-5 (98.77% accuracy)<n>DMC enables the first documented deployment of a standard CNN on the ATmega328P, a device constrained to 2KB, previously considered infeasible for CNN inference.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper introduces Deep Microcompression (DMC), a hardware-aware pipeline for deep learning inference on bare-metal microcontrollers. DMC integrates structured pruning, quantization-aware training, and fixed-length bit-packing to achieve a 55.8$\times$ weight compression ratio on LeNet-5 (98.77\% accuracy), generating a dependency-free C library with deterministic latency. On the RP2040 (Cortex-M0+), DMC reduces binary size by 3$\times$ versus TensorFlow Lite while matching its accuracy. Critically, DMC enables the first documented deployment of a standard CNN on the ATmega328P, a device constrained to 2KB SRAM, previously considered infeasible for CNN inference.

Related papers

• Benchmarking Composable Compression Techniques in Mixture-of-Experts LLMs [50.677556944160216]
  MoEXBench is a systematic benchmark for evaluating composable MoE compression as an end-to-end deployment workflow.<n>It measures composable-compression quality, workload and architecture, pruning/quantization/KV cache sensitivity, and deployment efficiency on commodity hardware.
  arXiv  Detail & Related papers  (2026-08-22T00:01:18Z)
• Lightweight PCGAE-Net: Parallel CrossGate Attention and Bottleneck AutoEncoder for Efficient 5G Channel Prediction [1.1083289076967893]
  This paper introduces Lightweight PCGAE-Net, which addresses the efficiency problem not by post-hoc compression but by correcting two architectural flaws in the current state of the art.<n>It produces a model with just 8.54,M parameters -- 58% fewer than the CS3T-UNet baseline.<n>It outperforms it by up to 3.26,dB at 5,km/h and 6.0,dB at 9,km/h in single-step prediction on QuaDriGa dataset.
  arXiv  Detail & Related papers  (2026-06-24T04:55:25Z)
• From Compression to Deployment: Real-Time and Energy-Efficient FastGRNN on Ultra-Constrained Microcontrollers [0.0]
  We present an end-to-end open-source reproduction of FastGRNN, a compact gated cell, deployed on two bare-metal targets.<n>The model occupies 566 bytes of weights and achieves macro F1 = 0.918 (seed 0; five-seed Q15 mean 0.853+-0.107) on the HAPT test set.<n>Both platforms sustain real-time 50 Hz streaming inference (9.21 ms per sample on Arduino; 13 ms on MSP430), where a 256-entry sigmoid/tanh look-up table delivers a 30.5x speedup.
  arXiv  Detail & Related papers  (2026-06-15T19:49:38Z)
• On-Device Vision Training, Deployment, and Inference on a Thumb-Sized Microcontroller [0.0]
  This paper presents an end-to-end on-device vision machine learning pipeline, executing entirely on a microcontroller-class device costing $15-40 USD.<n>Running on the Seeed Studio ESP32-S3 XI Kit MLAO (8 MB PSRAM), the firmware achieves three-class 64x64 image classification in approximately 9 minutes per training run, with real-time inference at 6.3 FPS.
  arXiv  Detail & Related papers  (2026-04-24T20:59:16Z)
• Pushing the Limits of On-Device Streaming ASR: A Compact, High-Accuracy English Model for Low-Latency Inference [5.685908474026849]
  High-quality automatic speech recognition (ASR) on edge devices requires models that jointly optimize accuracy, latency, and memory footprint while operating entirely on CPU without GPU acceleration.<n>We conduct a systematic empirical study of state-of-the-art ASR architectures, encompassing encoder-decoder, transducer, and LLM-based paradigms, evaluated across batch, chunked, and streaming inference modes.<n>Our recommended configuration, the int4 k-quant variant, achieves 8.20% average streaming WER across eight standard benchmarks, running comfortably faster than real-time on CPU with 0.56 s algorithmic latency.
  arXiv  Detail & Related papers  (2026-04-16T00:04:32Z)
• 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)
• NanoCockpit: Performance-optimized Application Framework for AI-based Autonomous Nanorobotics [50.594459728605734]
  Small form factor, i.e., a few 10s grams, severely limits onboard computational resources to sub-SI100milliwatt microcontroller units (MCUs)<n>Our framework achieves ideal end-to-end latency, i.e. zero overhead due to serialized tasks, delivering quantifiable improvements in closed-loop control performance.
  arXiv  Detail & Related papers  (2026-01-12T12:29:38Z)
• MC#: Mixture Compressor for Mixture-of-Experts Large Models [86.64315380917827]
  Mixture-of-Experts (MoE) effectively scales large language models (LLMs) and vision-language models (VLMs) by increasing capacity through sparse activation.<n>We propose MC# (Mixture-Compressor-sharp), a framework that combines static quantization and dynamic expert pruning.
  arXiv  Detail & Related papers  (2025-10-13T03:12:46Z)
• 70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float [52.079202872069835]
  Large-scale AI models, such as Large Language Models (LLMs) and Diffusion Models (DMs) have grown rapidly in size.<n>We introduce Dynamic-Length Float (DFloat11), a compression framework that reduces LLM and DM size by 30% while preserving outputs that are bit-for-bit identical to the original model.
  arXiv  Detail & Related papers  (2025-04-15T22:38:38Z)
• Data-Free Dynamic Compression of CNNs for Tractable Efficiency [46.498278084317704]
  structured pruning approaches have shown promise in lowering floating-point operations without substantial drops in accuracy.<n>We propose HASTE (Hashing for Tractable Efficiency), a data-free, plug-and-play convolution module that instantly reduces a network's test-time inference cost without training or fine-tuning.<n>We demonstrate our approach on the popular vision benchmarks CIFAR-10 and ImageNet, where we achieve a 46.72% reduction in FLOPs with only a 1.25% loss in accuracy.
  arXiv  Detail & Related papers  (2023-09-29T13:09:40Z)
• Keyword Spotting System and Evaluation of Pruning and Quantization Methods on Low-power Edge Microcontrollers [7.570300579676175]
  Keywords spotting (KWS) is beneficial for voice-based user interactions with low-power devices at the edge. This paper shows our small-footprint KWS system running on STM32F7 microcontroller with Cortex-M7 core @216MHz and 512KB static RAM.
  arXiv  Detail & Related papers  (2022-08-04T16:49:45Z)
• CrAM: A Compression-Aware Minimizer [103.29159003723815]
  We propose a new compression-aware minimizer dubbed CrAM that modifies the optimization step in a principled way. CrAM produces dense models that can be more accurate than the standard SGD/Adam-based baselines, but which are stable under weight pruning. CrAM can produce sparse models which perform well for transfer learning, and it also works for semi-structured 2:4 pruning patterns supported by GPU hardware.
  arXiv  Detail & Related papers  (2022-07-28T16:13:28Z)
• 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)

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.