paper-with-me

Papers

Improving Low-Precision Network Quantization via Bin Regularization

2021-01-01 · ICCV 2021 10 · Tiantian Han, Dong Li, Ji Liu, Lu Tian, Yi Shan

Model quantization is an important mechanism for energy-efficient deployment of deep neural networks on resource-constrained devices by reducing the bit precision of weights and activations. However, it remains challenging to maintain high accuracy as bit precision decreases, especially for low-precision networks (e.g., 2-bit MobileNetV2). Existing methods have explored to address this problem by minimizing the quantization error or mimicking the data distribution of full-precision networks. In this work, we propose a novel weight regularization algorithm for improving low-precision network quantization. Instead of constraining the overall data distribution, we separably optimize all elements in each quantization bin to be as close to the target quantized value as possible. Such bin regularization (BR) mechanism encourages the weight distribution of each quantization bin to be sharp and approximate to a Dirac delta distribution ideally. Experiments demonstrate that our method achieves consistent improvements over the state-of-the-art quantization-aware training methods for different low-precision networks. Particularly, our bin regularization improves LSQ for 2-bit MobileNetV2 and MobileNetV3-Small by 3.9% and 4.9% top-1 accuracy on ImageNet, respectively.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Methods 이 논문이 사용한 방법론

Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Batch Normalization 설명 없음
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution
Inverted Residual Block 설명 없음
Average Pooling 설명 없음
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…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Similar Papers 제목 키워드 기반

CSQ: Growing Mixed-Precision Quantization Scheme with Bi-level Continuous Sparsification

2022-12-06 · Lirui Xiao, Huanrui Yang, Zhen Dong, Kurt Keutzer 외

Mixed-precision quantization has been widely applied on deep neural networks (DNNs) as it leads to significantly better efficiency-accuracy tradeoffs compared to uniform quantization. Meanwhile, determining the exact pre…

Quantization

Time regularization as a solution to mitigate quantization induced performance degradation

2020-10-30

Reset control is known to be able to outperform PID and the like linear controllers. However, in motion control systems, quantization can cause severe performance degradation. This paper shows the application of time reg…

Quantization

QReg: On Regularization Effects of Quantization

2022-06-24 · MohammadHossein AskariHemmat, Reyhane Askari Hemmat, Alex Hoffman, Ivan Lazarevich 외

In this paper we study the effects of quantization in DNN training. We hypothesize that weight quantization is a form of regularization and the amount of regularization is correlated with the quantization level (precisio…

FormQuantization

Learning Sparse Low-Precision Neural Networks With Learnable Regularization

2018-09-01 · Yoojin Choi, Mostafa El-Khamy, Jungwon Lee

We consider learning deep neural networks (DNNs) that consist of low-precision weights and activations for efficient inference of fixed-point operations. In training low-precision networks, gradient descent in the backwa…

Image Super-ResolutionL2 RegularizationQuantizationSuper-Resolution

Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss

2021-09-05 · ICCV 2021 10 · Jung Hyun Lee, Jihun Yun, Sung Ju Hwang, Eunho Yang

Network quantization, which aims to reduce the bit-lengths of the network weights and activations, has emerged for their deployments to resource-limited devices. Although recent studies have successfully discretized a fu…

Quantization