Neural Architecture Search (NAS)

Projects

MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning

NeurIPS 2021

In MCUNetV2, we propose a generic patch-by-patch inference scheduling, which operates only on a small spatial region of the feature map and significantly cuts down the peak memory. We further propose network redistribution to shift the receptive field and FLOPs to the later stage and reduce the computation overhead.

Anycost GANs for Interactive Image Synthesis and Editing

CVPR 2021

(

)

Anycost GAN generates consistent outputs under various, fine-grained computation budgets.

Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

ECCV 2020

(

)

SPVNAS enhances Point-Voxel Convolution in large-scale outdoor scenes with sparse convolutions. With 3D Neural Architecture Search (3D-NAS), it efficiently and effectively searches the optimal 3D neural network architecture under a given resource constraint.

MCUNet: Tiny Deep Learning on IoT Devices

MCUNet is a system-algorithm co-design framework for tiny deep learning on microcontrollers. It consists of TinyNAS and TinyEngine. They are co-designed to fit the tight memory budgets. With system-algorithm co-design, we can significantly improve the deep learning performance on the same tiny memory budget.

APQ: Joint Search for Nerwork Architecture, Pruning and Quantization Policy

CVPR 2020

(

)

APQ is an efficient AutoML framework for joint optimization of neural architecture, pruning, and quantization.

GAN Compression: Efficient Architectures for Interactive Conditional GANs

CVPR 2020 & TPAMI

(

)

A general-purpose compression framework for reducing the inference time and model size of the generator in conditional GANs.

Blog Posts

On-Device Training Under 256KB Memory

November 28, 2022

In MCUNetV3, we enable on-device training under 256KB SRAM and 1MB Flash, using less than 1/1000 memory of PyTorch while matching the accuracy on the visual wake words application. It enables the model to adapt to newly collected sensor data and users can enjoy customized services without uploading the data to the cloud thus protecting privacy.

Reducing the carbon footprint of AI using the Once-for-All network

July 3, 2020

“The aim is smaller, greener neural networks,” says Song Han, an assistant professor in the Department of Electrical Engineering and Computer Science. “Searching efficient neural network architectures has until now had a huge carbon footprint. But we reduced that footprint by orders of magnitude with these new methods.”

Auto Hardware-Aware Neural Network Specialization on ImageNet in Minutes

July 2, 2020

This tutorial introduces how to use the Once-for-All (OFA) Network to get specialized ImageNet models for the target hardware in minutes with only your laptop.

Efficiently Understanding Videos, Point Cloud and Natural Language on NVIDIA Jetson Xavier NX

May 22, 2020

Thanks to NVIDIA’s amazing deep learning eco-system, we are able to deploy three applications on Jetson Xavier NX soon after we receive the kit, including efficient video understanding with Temporal Shift Module (TSM, ICCV’19), efficient 3D deep learning with Point-Voxel CNN (PVCNN, NeurIPS’19), and efficient machine translation with hardware-aware transformer (HAT, ACL’20).