Uniform-precision neural network quantization has gained popularity since it simplifies densely packed arithmetic unit for high computing capability. However, it ignores heterogeneous sensitivity to the impact of quantization errors across the layers, resulting in sub-optimal inference accuracy. This work proposes a novel neural architecture search called neural channel expansion that adjusts the network structure to alleviate accuracy degradation from ultra-low uniform-precision quantization. The proposed method selectively expands channels for the quantization sensitive layers while satisfying hardware constraints (e.g., FLOPs, PARAMs). Based on in-depth analysis and experiments, we demonstrate that the proposed method can adapt several popular networks channels to achieve superior 2-bit quantization accuracy on CIFAR10 and ImageNet. In particular, we achieve the best-to-date Top-1/Top-5 accuracy for 2-bit ResNet50 with smaller FLOPs and the parameter size.

翻译：均匀精度神经网络量化因其简化了高计算能力的密集算术单元而受到关注。然而，它忽略了各层对量化误差影响的异构敏感性，导致推理次优精度。本工作提出一种名为神经通道扩展的新型神经架构搜索方法，通过调整网络结构来缓解超低均匀精度量化导致的精度下降。该方法在满足硬件约束（如FLOPs、PARAMs）的同时，为量化敏感层选择性扩展通道。基于深入分析与实验，我们证明所提方法能够适配多种流行网络的通道，在CIFAR10和ImageNet上实现卓越的2比特量化精度。特别地，我们在2比特ResNet50上以更小的FLOPs和参数规模取得了迄今最佳Top-1/Top-5精度。