Wake Vision pipeline produces a 6M-image person detection dataset for TinyML with 2.2% label error, improving model accuracy up to 6.6% over prior VWW benchmark across architectures and subsets.
Visual Wake Words Dataset
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
The emergence of Internet of Things (IoT) applications requires intelligence on the edge. Microcontrollers provide a low-cost compute platform to deploy intelligent IoT applications using machine learning at scale, but have extremely limited on-chip memory and compute capability. To deploy computer vision on such devices, we need tiny vision models that fit within a few hundred kilobytes of memory footprint in terms of peak usage and model size on device storage. To facilitate the development of microcontroller friendly models, we present a new dataset, Visual Wake Words, that represents a common microcontroller vision use-case of identifying whether a person is present in the image or not, and provides a realistic benchmark for tiny vision models. Within a limited memory footprint of 250 KB, several state-of-the-art mobile models achieve accuracy of 85-90% on the Visual Wake Words dataset. We anticipate the proposed dataset will advance the research on tiny vision models that can push the pareto-optimal boundary in terms of accuracy versus memory usage for microcontroller applications.
verdicts
UNVERDICTED 5representative citing papers
A survey of on-device learning in TinyML organized by distribution change regimes, highlighting influences on applications, hardware, and solutions plus a gap between benchmarks and deployments.
FrequencyFormer co-designs a multi-scale DCT tokenizer, LUT-based near-sensor hardware, and modified MIPI communication to enable frequency-domain ViT inference with up to 128x data reduction and 230x lower communication energy.
A lightweight HW-NAS produces tiny CNNs for ultra-low-power MCUs that match state-of-the-art accuracy on three tiny computer vision benchmarks.
A HW-NAS framework executable on resource-limited embedded devices generates optimized CNNs for low-end MCUs and reports state-of-the-art human-recognition accuracy on the Visual Wake Word dataset.
citing papers explorer
-
Wake Vision: A Tailored Dataset and Benchmark Suite for TinyML Computer Vision Applications
Wake Vision pipeline produces a 6M-image person detection dataset for TinyML with 2.2% label error, improving model accuracy up to 6.6% over prior VWW benchmark across architectures and subsets.
-
What changes after deployment? A survey on On-device Learning in TinyML
A survey of on-device learning in TinyML organized by distribution change regimes, highlighting influences on applications, hardware, and solutions plus a gap between benchmarks and deployments.
-
FrequencyFormer: A Co-Designed Sensor-to-Processor Pipeline for Frequency-Domain Vision Transformer Inference
FrequencyFormer co-designs a multi-scale DCT tokenizer, LUT-based near-sensor hardware, and modified MIPI communication to enable frequency-domain ViT inference with up to 128x data reduction and 230x lower communication energy.
-
An affordable hardware-aware neural architecture search for deploying convolutional neural networks on ultra-low-power computing platforms
A lightweight HW-NAS produces tiny CNNs for ultra-low-power MCUs that match state-of-the-art accuracy on three tiny computer vision benchmarks.
-
Running hardware-aware neural architecture search on embedded devices under 512MB of RAM
A HW-NAS framework executable on resource-limited embedded devices generates optimized CNNs for low-end MCUs and reports state-of-the-art human-recognition accuracy on the Visual Wake Word dataset.