OpenGlass is an open-source smart glasses platform using event-based vision and event-driven power management to achieve 11.5 hours of continuous on-device ML on a 200 mAh battery, demonstrated with 83.94% cross-subject hand gesture accuracy.
MCUNet: Tiny Deep Learning on IoT Devices , publisher =
4 Pith papers cite this work, alongside 257 external citations. Polarity classification is still indexing.
4
Pith papers citing it
257
external citations · Pith
abstract
Machine learning on tiny IoT devices based on microcontroller units (MCU) is appealing but challenging: the memory of microcontrollers is 2-3 orders of magnitude smaller even than mobile phones. We propose MCUNet, a framework that jointly designs the efficient neural architecture (TinyNAS) and the lightweight inference engine (TinyEngine), enabling ImageNet-scale inference on microcontrollers. TinyNAS adopts a two-stage neural architecture search approach that first optimizes the search space to fit the resource constraints, then specializes the network architecture in the optimized search space. TinyNAS can automatically handle diverse constraints (i.e.device, latency, energy, memory) under low search costs.TinyNAS is co-designed with TinyEngine, a memory-efficient inference library to expand the search space and fit a larger model. TinyEngine adapts the memory scheduling according to the overall network topology rather than layer-wise optimization, reducing the memory usage by 4.8x, and accelerating the inference by 1.7-3.3x compared to TF-Lite Micro and CMSIS-NN. MCUNet is the first to achieves >70% ImageNet top1 accuracy on an off-the-shelf commercial microcontroller, using 3.5x less SRAM and 5.7x less Flash compared to quantized MobileNetV2 and ResNet-18. On visual&audio wake words tasks, MCUNet achieves state-of-the-art accuracy and runs 2.4-3.4x faster than MobileNetV2 and ProxylessNAS-based solutions with 3.7-4.1x smaller peak SRAM. Our study suggests that the era of always-on tiny machine learning on IoT devices has arrived. Code and models can be found here: https://tinyml.mit.edu.
years
2026 4representative citing papers
Privatar uses horizontal frequency partitioning and distribution-aware minimal perturbation to enable private offloading of VR avatar reconstruction, supporting 2.37x more users with modest overhead.
Under a 1 MB activation budget, an F-Clip-style center-length-angle CNN with int8 QAT, TTA, and a LoI verifier reaches sAP10=24.1 on ShanghaiTech Wireframe.
Decision-level fusion with WBF outperforms feature-level fusion for occlusion-robust detection on ultra-low-end hardware, with gains up to +0.3827 mAP across three views and on-device execution on Coral boards.
citing papers explorer
-
OpenGlass: Ultra-Low-Power On-Device AI Eyewear with Event-based Vision
OpenGlass is an open-source smart glasses platform using event-based vision and event-driven power management to achieve 11.5 hours of continuous on-device ML on a 200 mAh battery, demonstrated with 83.94% cross-subject hand gesture accuracy.
-
Privatar: Scalable Privacy-preserving Multi-user VR via Secure Offloading
Privatar uses horizontal frequency partitioning and distribution-aware minimal perturbation to enable private offloading of VR avatar reconstruction, supporting 2.37x more users with modest overhead.
-
MiLSD: A Micro Line-Segment Detector for Resource-Constrained Devices
Under a 1 MB activation budget, an F-Clip-style center-length-angle CNN with int8 QAT, TTA, and a LoI verifier reaches sAP10=24.1 on ShanghaiTech Wireframe.
-
Tiny Collaborative Inference for Occlusion-Robust Object Detection
Decision-level fusion with WBF outperforms feature-level fusion for occlusion-robust detection on ultra-low-end hardware, with gains up to +0.3827 mAP across three views and on-device execution on Coral boards.