Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search

TL;DR

This paper introduces a differentiable neural architecture search method to optimize mixed-precision quantization of ConvNets, significantly reducing model size and computational cost while maintaining or improving accuracy.

Contribution

It proposes a novel differentiable NAS framework for mixed-precision quantization, enabling efficient exploration of layer-wise bit-width configurations.

Findings

Surpasses state-of-the-art ResNet compression on CIFAR-10 and ImageNet.

Achieves 21.1x smaller model size with better performance.

Reduces computational cost by 103.9x while outperforming baseline models.

Abstract

Recent work in network quantization has substantially reduced the time and space complexity of neural network inference, enabling their deployment on embedded and mobile devices with limited computational and memory resources. However, existing quantization methods often represent all weights and activations with the same precision (bit-width). In this paper, we explore a new dimension of the design space: quantizing different layers with different bit-widths. We formulate this problem as a neural architecture search problem and propose a novel differentiable neural architecture search (DNAS) framework to efficiently explore its exponential search space with gradient-based optimization. Experiments show we surpass the state-of-the-art compression of ResNet on CIFAR-10 and ImageNet. Our quantized models with 21.1x smaller model size or 103.9x lower computational cost can still outperform baseline quantized or even full precision models.