Related papers: Automatic Network Adaptation for Ultra-Low Uniform…
This work investigates how using reduced precision data in Convolutional Neural Networks (CNNs) affects network accuracy during classification. More specifically, this study considers networks where each layer may use different precision…
This paper proposes two novel techniques to train deep convolutional neural networks with low bit-width weights and activations. First, to obtain low bit-width weights, most existing methods obtain the quantized weights by performing…
Automatic designing computationally efficient neural networks has received much attention in recent years. Existing approaches either utilize network pruning or leverage the network architecture search methods. This paper presents a new…
We introduce a precision polarization scheme for DNN inference that utilizes only very low and very high precision levels, assigning low precision to the majority of network weights and activations while reserving high precision paths for…
Multi-bit quantization networks enable flexible deployment of deep neural networks by supporting multiple precision levels within a single model. However, existing approaches suffer from significant training overhead as full-dataset updates…
We study how to set channel numbers in a neural network to achieve better accuracy under constrained resources (e.g., FLOPs, latency, memory footprint or model size). A simple and one-shot solution, named AutoSlim, is presented. Instead of…
The inherent heavy computation of deep neural networks prevents their widespread applications. A widely used method for accelerating model inference is quantization, by replacing the input operands of a network using fixed-point values.…
Quantized Neural Networks (QNNs) use low bit-width fixed-point numbers for representing weight parameters and activations, and are often used in real-world applications due to their saving of computation resources and reproducibility of…
Modern neural networks are over-parametrized. In particular, each rectified linear hidden unit can be modified by a multiplicative factor by adjusting input and output weights, without changing the rest of the network. Inspired by the…
Neural network quantization and pruning are two techniques commonly used to reduce the computational complexity and memory footprint of these models for deployment. However, most existing pruning strategies operate on full-precision and…
Deep neural networks (DNNs) are nowadays ubiquitous in many domains such as computer vision. However, due to their high latency, the deployment of DNNs hinges on the development of compression techniques such as quantization which consists…
High image resolution is critical to obtain a good performance in many computer vision applications. Computational complexity of CNNs, however, grows significantly with the increase in input image size. Here, we show that it is almost…
Quantized neural networks typically require smaller memory footprints and lower computation complexity, which is crucial for efficient deployment. However, quantization inevitably leads to a distribution divergence from the original…
This paper presents incremental network quantization (INQ), a novel method, targeting to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version whose weights are constrained…
This paper introduces a post-training quantization~(PTQ) method achieving highly efficient Convolutional Neural Network~ (CNN) quantization with high performance. Previous PTQ methods usually reduce compression error via performing…
Efficient model inference is an important and practical issue in the deployment of deep neural network on resource constraint platforms. Network quantization addresses this problem effectively by leveraging low-bit representation and…
Quantized Neural Networks (QNNs), which use low bitwidth numbers for representing parameters and performing computations, have been proposed to reduce the computation complexity, storage size and memory usage. In QNNs, parameters and…
Quantization of neural networks has become common practice, driven by the need for efficient implementations of deep neural networks on embedded devices. In this paper, we exploit an oft-overlooked degree of freedom in most networks - for a…
Target classification is a fundamental task in radar systems, and its performance critically depends on the quantization precision of the signal. While high-precision quantization (e.g. 16-bit) is well established, 1-bit quantization offers…
Neural network quantization is a promising compression technique to reduce memory footprint and save energy consumption, potentially leading to real-time inference. However, there is a performance gap between quantized and full-precision…