A low precision deep neural network training technique for producing sparse, ternary neural networks is presented. The technique incorporates hard- ware implementation costs during training to achieve significant model compression for inference. Training involves three stages: network training using L2 regularization and a quantization threshold regularizer, quantization pruning, and finally retraining. Resulting networks achieve improved accuracy, reduced memory footprint and reduced computational complexity compared with conventional methods, on MNIST and CIFAR10 datasets. Our networks are up to 98% sparse and 5 & 11 times smaller than equivalent binary and ternary models, translating to significant resource and speed benefits for hardware implementations.
IIT Kanpur（印度理工学院坎普尔分校）；R&D Center, Hitachi India Pvt. Ltd.（日立印度私人有限公司研发中心）；Indian Institute of Technology, Kanpur（印度理工学院坎普尔分校）
We propose a framework for compressing state-of-the-art Single Shot MultiBox Detector (SSD). The framework addresses compression in the following stages: Sparsity Induction, Filter Selection, and Filter Pruning. In the Sparsity Induction stage, the object detector model is sparsified via an improved global threshold. In Filter Selection & Pruning stage, we select and remove filters using sparsity statistics of filter weights in two consecutive convolutional layers. This results in the model with the size smaller than most existing compact architectures. We evaluate the performance of our frame…
Neural networks can be compressed to reduce memory and computational requirements, or to increase accuracy by facilitating the use of a larger base architecture. In this paper we focus on pruning individual neurons, which can simultaneously trim model size, FLOPs, and run-time memory. To improve upon the performance of existing compression algorithms we utilize the information bottleneck principle instantiated via a tractable variational bound. Minimization of this information theoretic bound reduces the redundancy between adjacent layers by aggregating useful information into a subset of neur…
Fujian Key Laboratory of Sensing and Computing for Smart City, Department of Cognitive ScienceSchool of Information Science and Engineering, Xiamen University（厦门大学信息科学与技术学院认知科学系智能城市感知与计算福建省重点实验室）；Beihang University（北京航空航天大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；University at Buffalo（布法罗大学）；BestImage, Tencent Technology (Shanghai) Co.,Ltd（腾讯科技（上海）有限公司）；Peng Cheng Laboratory（鹏城实验室）
Compressing convolutional neural networks (CNNs) has received ever-increasing research focus. However, most existing CNN compression methods do not interpret their inherent structures to distinguish the implicit redundancy. In this paper, we investigate the problem of CNN compression from a novel interpretable perspective. The relationship between the input feature maps and 2D kernels is revealed in a theoretical framework, based on which a kernel sparsity and entropy (KSE) indicator is proposed to quantitate the feature map importance in a feature-agnostic manner to guide model compression. K…
Advances in Implicit Neural Representations (INR) have motivated research on domain-agnostic compression techniques. These methods train a neural network to approximate an object, and then store the weights of the trained model. For example, given an image, a network is trained to learn the mapping from pixel locations to RGB values. In this paper, we propose L$_0$onie, a sparsity-constrained extension of the COIN compression method. Sparsity allows to leverage the faster learning of overparameterized networks, while retaining the desirable compression rate of smaller models. Moreover, our con…
Generative Adversarial Networks (GANs) have achieved huge success in generating high-fidelity images, however, they suffer from low efficiency due to tremendous computational cost and bulky memory usage. Recent efforts on compression GANs show noticeable progress in obtaining smaller generators by sacrificing image quality or involving a time-consuming searching process. In this work, we aim to address these issues by introducing a teacher network that provides a search space in which efficient network architectures can be found, in addition to performing knowledge distillation. First, we revi…
DNN-based frame interpolation, which generates intermediate frames from two consecutive frames, is often dependent on model architectures with a large number of features, preventing their deployment on systems with limited resources, such as mobile devices. We present a compression-driven network design for frame interpolation that leverages model pruning through sparsity-inducing optimization to greatly reduce the model size while attaining higher performance. Concretely, we begin by compressing the recently proposed AdaCoF model and demonstrating that a 10 times compressed AdaCoF performs si…
University of Waterloo（滑铁卢大学）；University of Toronto（多伦多大学）
Deploying deep Convolutional Neural Networks (CNNs) is impacted by their memory footprint and speed requirements, which mainly come from convolution. Widely-used convolution algorithms, im2col and MEC, produce a lowered matrix from an activation map by redundantly storing the map's elements included at horizontal and/or vertical kernel overlappings without considering the sparsity of the map. Using the sparsity of the map, this paper proposes two new convolution algorithms dubbed Compressed Pattern Overlap (CPO) and Compressed Pattern Sets (CPS) that simultaneously decrease the memory footprin…
Institute for Infocomm Research, Agency for Science, Technology and Research（新加坡科技研究局资讯通信研究院）；College of Computer Science, Sichuan University（四川大学计算机学院）；Nanyang Technological University（南洋理工大学）
As Deep Neural Networks (DNNs) usually are overparameterized and have millions of weight parameters, it is challenging to deploy these large DNN models on resource-constrained hardware platforms, e.g., smartphones. Numerous network compression methods such as pruning and quantization are proposed to reduce the model size significantly, of which the key is to find suitable compression allocation (e.g., pruning sparsity and quantization codebook) of each layer. Existing solutions obtain the compression allocation in an iterative/manual fashion while finetuning the compressed model, thus sufferin…
3DQ: Compact Quantized Neural Networks for Volumetric Whole Brain Segmentation
Technical University of Munich（慕尼黑工业大学）；Ludwig Maximilian University（路德维希-马克西米利安大学）；University of California Berkeley（加州大学伯克利分校）；Johns Hopkins University（约翰斯·霍普金斯大学）
本文提出三值量化方法 3DQ，首次用于三维 F-CNN，在全脑分割任务及 3D U-Net、V-Net 上实现 16 倍压缩并保持全精度性能。
Tsinghua University（清华大学）；University of California, Santa Barbara（加州大学圣巴巴拉分校）
There is a pressing need to build an architecture that could subsume these networks under a unified framework that achieves both higher performance and less overhead. To this end, two fundamental issues are yet to be addressed. The first one is how to implement the back propagation when neuronal activations are discrete. The second one is how to remove the full-precision hidden weights in the training phase to break the bottlenecks of memory/computation consumption. To address the first issue, we present a multi-step neuronal activation discretization method and a derivative approximation tech…
University of California, Irvine（加州大学欧文分校）；The University of Utah（犹他大学）
Deep Neural Networks (DNNs) needs to be both efficient and robust for practical uses. Quantization and structure simplification are promising ways to adapt DNNs to mobile devices, and adversarial training is the most popular method to make DNNs robust. In this work, we try to obtain both features by applying a convergent relaxation quantization algorithm, Binary-Relax (BR), to a robust adversarial-trained model, ResNets Ensemble via Feynman-Kac Formalism (EnResNet). We also discover that high precision, such as ternary (tnn) and 4-bit, quantization will produce sparse DNNs. However, this spars…
Convolutional neural networks (CNNs) have developed to become powerful models for various computer vision tasks ranging from object detection to semantic segmentation. However, most of the state-of-the-art CNNs cannot be deployed directly on edge devices such as smartphones and drones, which need low latency under limited power and memory bandwidth. One popular, straightforward approach to compressing CNNs is network slimming, which imposes $\ell_1$ regularization on the channel-associated scaling factors via the batch normalization layers during training. Network slimming thereby identifies i…
This paper describes a channel-selection approach for simplifying deep neural networks. Specifically, we propose a new type of generic network layer, called pruning layer, to seamlessly augment a given pre-trained model for compression. Each pruning layer, comprising $1 \times 1$ depth-wise kernels, is represented with a dual format: one is real-valued and the other is binary. The former enables a two-phase optimization process of network pruning to operate with an end-to-end differentiable network, and the latter yields the mask information for channel selection. Our method progressively perf…
University of Central Florida（中佛罗里达大学）；Tencent AI lab（腾讯人工智能实验室）
Deep convolution neural network has achieved great success in many artificial intelligence applications. However, its enormous model size and massive computation cost have become the main obstacle for deployment of such powerful algorithm in the low power and resource-limited embedded systems. As the countermeasure to this problem, in this work, we propose statistical weight scaling and residual expansion methods to reduce the bit-width of the whole network weight parameters to ternary values (i.e. -1, 0, +1), with the objectives to greatly reduce model size, computation cost and accuracy degr…
Tencent Media Lab（腾讯媒体实验室）；Northeastern University（东北大学）
Compressing Deep Neural Network (DNN) models to alleviate the storage and computation requirements is essential for practical applications, especially for resource limited devices. Although capable of reducing a reasonable amount of model parameters, previous unstructured or structured weight pruning methods can hardly truly accelerate inference, either due to the poor hardware compatibility of the unstructured sparsity or due to the low sparse rate of the structurally pruned network. Aiming at reducing both storage and computation, as well as preserving the original task performance, we propo…
Peking University（北京大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）；Peng Cheng Laboratory（鹏城实验室）
Spiking neural networks (SNNs) with event-based computation are promising brain-inspired models for energy-efficient applications on neuromorphic hardware. However, most supervised SNN training methods, such as conversion from artificial neural networks or direct training with surrogate gradients, require complex computation rather than spike-based operations of spiking neurons during training. In this paper, we study spike-based implicit differentiation on the equilibrium state (SPIDE) that extends the recently proposed training method, implicit differentiation on the equilibrium state (IDE),…
