paper-with-me

홈 › Papers

Redistribution of Weights and Activations for AdderNet Quantization

2022-12-20 · Ying Nie, Kai Han, Haikang Diao, Chuanjian Liu, Enhua Wu, Yunhe Wang

Adder Neural Network (AdderNet) provides a new way for developing energy-efficient neural networks by replacing the expensive multiplications in convolution with cheaper additions (i.e.l1-norm). To achieve higher hardware efficiency, it is necessary to further study the low-bit quantization of AdderNet. Due to the limitation that the commutative law in multiplication does not hold in l1-norm, the well-established quantization methods on convolutional networks cannot be applied on AdderNets. Thus, the existing AdderNet quantization techniques propose to use only one shared scale to quantize both the weights and activations simultaneously. Admittedly, such an approach can keep the commutative law in the l1-norm quantization process, while the accuracy drop after low-bit quantization cannot be ignored. To this end, we first thoroughly analyze the difference on distributions of weights and activations in AdderNet and then propose a new quantization algorithm by redistributing the weights and the activations. Specifically, the pre-trained full-precision weights in different kernels are clustered into different groups, then the intra-group sharing and inter-group independent scales can be adopted. To further compensate the accuracy drop caused by the distribution difference, we then develop a lossless range clamp scheme for weights and a simple yet effective outliers clamp strategy for activations. Thus, the functionality of full-precision weights and the representation ability of full-precision activations can be fully preserved. The effectiveness of the proposed quantization method for AdderNet is well verified on several benchmarks, e.g., our 4-bit post-training quantized adder ResNet-18 achieves an 66.5% top-1 accuracy on the ImageNet with comparable energy efficiency, which is about 8.5% higher than that of the previous AdderNet quantization methods.

📄 PDF Abstract BibTeX arXiv:2212.10200

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Towards Stable and Robust AdderNets

2021-12-01 · NeurIPS 2021 12 · Minjing Dong, Yunhe Wang, Xinghao Chen, Chang Xu

Adder neural network (AdderNet) replaces the original convolutions with massive multiplications by cheap additions while achieving comparable performance thus yields a series of energy-efficient neural networks. Compared…

Adversarial Robustness

AdderNet and its Minimalist Hardware Design for Energy-Efficient Artificial Intelligence

2021-01-25 · Yunhe Wang, Mingqiang Huang, Kai Han, Hanting Chen 외

Convolutional neural networks (CNN) have been widely used for boosting the performance of many machine intelligence tasks. However, the CNN models are usually computationally intensive and energy consuming, since they ar…

Quantization

LadderNet: Multi-path networks based on U-Net for medical image segmentation

2018-10-17 · Juntang Zhuang

U-Net has been providing state-of-the-art performance in many medical image segmentation problems. Many modifications have been proposed for U-Net, such as attention U-Net, recurrent residual convolutional U-Net (R2-UNet…

DecoderImage SegmentationMedical Image SegmentationRetinal Vessel Segmentation+2

BiTAT: Neural Network Binarization with Task-dependent Aggregated Transformation

2022-07-04 · Geon Park, Jaehong Yoon, Haiyang Zhang, Xing Zhang 외

Neural network quantization aims to transform high-precision weights and activations of a given neural network into low-precision weights/activations for reduced memory usage and computation, while preserving the perform…

BinarizationQuantization

Quantizing deep convolutional networks for efficient inference: A whitepaper

2018-06-21 · Raghuraman Krishnamoorthi

We present an overview of techniques for quantizing convolutional neural networks for inference with integer weights and activations. Per-channel quantization of weights and per-layer quantization of activations to 8-bit…

Quantization