Improving weight sparsity is a common strategy for producing light-weight deep neural networks. However, pruning models with residual learning is more challenging. In this paper, we introduce Variance-Aware Cross-Layer (VACL), a novel approach to address this problem. VACL consists of two parts, a Cross-Layer grouping and a Variance Aware regularization. In Cross-Layer grouping the $i^{th}$ filters of layers connected by skip-connections are grouped into one regularization group. Then, the Variance-Aware regularization term takes into account both the first and second-order statistics of the connected layers to constrain the variance within a group. Our approach can effectively improve the structural sparsity of residual models. For CIFAR10, the proposed method reduces a ResNet model by up to 79.5% with no accuracy drop and reduces a ResNeXt model by up to 82% with less than 1% accuracy drop. For ImageNet, it yields a pruned ratio of up to 63.3% with less than 1% top-5 accuracy drop. Our experimental results show that the proposed approach significantly outperforms other state-of-the-art methods in terms of overall model size and accuracy.
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Network pruning is widely used to compress Deep Neural Networks (DNNs). The Soft Filter Pruning (SFP) method zeroizes the pruned filters during training while updating them in the next training epoch. Thus the trained information of the pruned filters is completely dropped. To utilize the trained pruned filters, we proposed a SofteR Filter Pruning (SRFP) method and its variant, Asymptotic SofteR Filter Pruning (ASRFP), simply decaying the pruned weights with a monotonic decreasing parameter. Our methods perform well across various networks, datasets and pruning rates, also transferable to weig…
Parameter pruning is a promising approach for CNN compression and acceleration by eliminating redundant model parameters with tolerable performance loss. Despite its effectiveness, existing regularization-based parameter pruning methods usually drive weights towards zero with large and constant regularization factors, which neglects the fact that the expressiveness of CNNs is fragile and needs a more gentle way of regularization for the networks to adapt during pruning. To solve this problem, we propose a new regularization-based pruning method (named IncReg) to incrementally assign different …
Regularization has long been utilized to learn sparsity in deep neural network pruning. However, its role is mainly explored in the small penalty strength regime. In this work, we extend its application to a new scenario where the regularization grows large gradually to tackle two central problems of pruning: pruning schedule and weight importance scoring. (1) The former topic is newly brought up in this work, which we find critical to the pruning performance while receives little research attention. Specifically, we propose an L2 regularization variant with rising penalty factors and show it …
The challenge of speeding up deep learning models during the deployment phase has been a large, expensive bottleneck in the modern tech industry. In this paper, we examine the use of both regularization and pruning for reduced computational complexity and more efficient inference in Deep Neural Networks (DNNs). In particular, we apply mixup and cutout regularizations and soft filter pruning to the ResNet architecture, focusing on minimizing floating-point operations (FLOPs). Furthermore, by using regularization in conjunction with network pruning, we show that such a combination makes a substa…
Northeastern University（东北大学）；Syracuse University（雪城大学）；College of William and Mary（威廉与玛丽学院）；DiDi AI Labs（滴滴人工智能实验室）
Accelerating DNN execution on various resource-limited computing platforms has been a long-standing problem. Prior works utilize l1-based group lasso or dynamic regularization such as ADMM to perform structured pruning on DNN models to leverage the parallel computing architectures. However, both of the pruning dimensions and pruning methods lack universality, which leads to degraded performance and limited applicability. To solve the problem, we propose a new block-based pruning framework that comprises a general and flexible structured pruning dimension as well as a powerful and efficient rew…
Zhejiang University（浙江大学）；SUTD-ZJU IDEA（新加坡科技设计大学-浙江大学 信息与数据科学联合实验室）；Singapore University of Technology and Design（新加坡科技设计大学）
Despite enjoying extensive applications in video analysis, three-dimensional convolutional neural networks (3D CNNs)are restricted by their massive computation and storage consumption. To solve this problem, we propose a threedimensional regularization-based neural network pruning method to assign different regularization parameters to different weight groups based on their importance to the network. Further we analyze the redundancy and computation cost for each layer to determine the different pruning ratios. Experiments show that pruning based on our method can lead to 2x theoretical speedu…
Network pruning in Convolutional Neural Networks (CNNs) has been extensively investigated in recent years. To determine the impact of pruning a group of filters on a network's accuracy, state-of-the-art pruning methods consistently assume filters of a CNN are independent. This allows the importance of a group of filters to be estimated as the sum of importances of individual filters. However, overparameterization in modern networks results in highly correlated filters that invalidate this assumption, thereby resulting in incorrect importance estimates. To address this issue, we propose OrthoRe…
Since the convolutional neural networks are often trained with redundant parameters, it is possible to reduce redundant kernels or filters to obtain a compact network without dropping the classification accuracy. In this paper, we propose a filter pruning method using the hierarchical group sparse regularization. It is shown in our previous work that the hierarchical group sparse regularization is effective in obtaining sparse networks in which filters connected to unnecessary channels are automatically close to zero. After training the convolutional neural network with the hierarchical group …
CERC, Polytechnique Montréal（蒙特利尔理工学院计算与工程研究中心）；University of Pisa（比萨大学）；Huawei Montreal Research Centre（华为蒙特利尔研究中心）；Jacobs Technion-Cornell Institute（雅各布斯泰克尼翁-康奈尔研究所）；Cornell Tech（康奈尔理工学院）；Technion - IIT（以色列理工学院）
In Machine Learning, Artificial Neural Networks (ANNs) are a very powerful tool, broadly used in many applications. Often, the selected (deep) architectures include many layers, and therefore a large amount of parameters, which makes training, storage and inference expensive. This motivated a stream of research about compressing the original networks into smaller ones without excessively sacrificing performances. Among the many proposed compression approaches, one of the most popular is \emph{pruning}, whereby entire elements of the ANN (links, nodes, channels, \ldots) and the corresponding we…
One-Cycle Structured Pruning via Stability-Driven Subnetwork Search
IT Application Research Center, Korea Electronics Technology Institute（韩国电子技术研究所应用信息技术中心）；Department of Intelligent Semiconductors, Soongsil University（顺慈大学智能半导体系）；Department of Computer Science & Engineering, Seoul National University（首尔国立大学计算机科学与工程系）
Electrostatic Force Regularization for Neural Structured Pruning
Université Polytechnique Hauts-de-France（上法兰西理工大学）；Université de Lille（里尔大学）；Université Paris Est Créteil（巴黎东克雷泰伊大学）；National Higher School of Biotechnology（国家高等生物技术学校）
Peking University（北京大学）；National Engineering Research Center of Visual Technology（视觉技术国家工程研究中心）；Peng Cheng Laboratory（鹏城实验室）
Soft threshold pruning is among the cutting-edge pruning methods with state-of-the-art performance. However, previous methods either perform aimless searching on the threshold scheduler or simply set the threshold trainable, lacking theoretical explanation from a unified perspective. In this work, we reformulate soft threshold pruning as an implicit optimization problem solved using the Iterative Shrinkage-Thresholding Algorithm (ISTA), a classic method from the fields of sparse recovery and compressed sensing. Under this theoretical framework, all threshold tuning strategies proposed in previ…
State-of-the-art computer vision models are rapidly increasing in capacity, where the number of parameters far exceeds the number required to fit the training set. This results in better optimization and generalization performance. However, the huge size of contemporary models results in large inference costs and limits their use on resource-limited devices. In order to reduce inference costs, convolutional filters in trained neural networks could be pruned to reduce the run-time memory and computational requirements during inference. However, severe post-training pruning results in degraded p…
DENSO CORPORATION（电装公司）；The University of Tokyo（东京大学）；AIP-RIKEN（AIP-理化学研究所）
Deep Neural Networks (DNNs) have recently been achieving state-of-the-art performance on a variety of computer vision related tasks. However, their computational cost limits their ability to be implemented in embedded systems with restricted resources or strict latency constraints. Model compression has therefore been an active field of research to overcome this issue. Additionally, DNNs typically require massive amounts of labeled data to be trained. This represents a second limitation to their deployment. Domain Adaptation (DA) addresses this issue by allowing knowledge learned on one labele…
To accelerate DNNs inference, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attempted to directly approximate a pre-trained model by low-rank decomposition; however, small approximation errors in parameters can ripple over a large prediction loss. Apparently, it is not optimal to separate low-rank approximation from training. Unlike previous works, this paper integrates low rank approximation and regularization into the training process. We propose Trained Rank Pruning (TRP), which alternates betw…
Dynamic model pruning is a recent direction that allows for the inference of a different sub-network for each input sample during deployment. However, current dynamic methods rely on learning a continuous channel gating through regularization by inducing sparsity loss. This formulation introduces complexity in balancing different losses (e.g task loss, regularization loss). In addition, regularization based methods lack transparent tradeoff hyperparameter selection to realize a computational budget. Our contribution is two-fold: 1) decoupled task and pruning losses. 2) Simple hyperparameter se…
Vision transformer has achieved competitive performance on a variety of computer vision applications. However, their storage, run-time memory, and computational demands are hindering the deployment to mobile devices. Here we present a vision transformer pruning approach, which identifies the impacts of dimensions in each layer of transformer and then executes pruning accordingly. By encouraging dimension-wise sparsity in the transformer, important dimensions automatically emerge. A great number of dimensions with small importance scores can be discarded to achieve a high pruning ratio without …
Shanghai Jiao Tong University（上海交通大学）；Qualcomm AI Research（高通人工智能研究）；Duke University（杜克大学）
The performance of Deep Neural Networks (DNNs) keeps elevating in recent years with increasing network depth and width. To enable DNNs on edge devices like mobile phones, researchers proposed several network compression methods including pruning, quantization and factorization. Among the factorization-based approaches, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attempted to directly approximate a pre-trained model by low-rank decomposition; however, small approximation errors in parameters can …
In this paper, we analyze two popular network compression techniques, i.e. filter pruning and low-rank decomposition, in a unified sense. By simply changing the way the sparsity regularization is enforced, filter pruning and low-rank decomposition can be derived accordingly. This provides another flexible choice for network compression because the techniques complement each other. For example, in popular network architectures with shortcut connections (e.g. ResNet), filter pruning cannot deal with the last convolutional layer in a ResBlock while the low-rank decomposition methods can. In addit…
Weight pruning methods of DNNs have been demonstrated to achieve a good model pruning rate without loss of accuracy, thereby alleviating the significant computation/storage requirements of large-scale DNNs. Structured weight pruning methods have been proposed to overcome the limitation of irregular network structure and demonstrated actual GPU acceleration. However, in prior work the pruning rate (degree of sparsity) and GPU acceleration are limited (to less than 50%) when accuracy needs to be maintained. In this work,we overcome these limitations by proposing a unified, systematic framework o…
Shanghai Jiao Tong University（上海交通大学）；Qualcomm AI Research（高通人工智能研究院）；Duke University（杜克大学）
To enable DNNs on edge devices like mobile phones, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attempted to directly approximate a pretrained model by low-rank decomposition; however, small approximation errors in parameters can ripple over a large prediction loss. As a result, performance usually drops significantly and a sophisticated effort on fine-tuning is required to recover accuracy. Apparently, it is not optimal to separate low-rank approximation from training. Unlike previous works, thi…
Convolutional neural networks (CNNs) are typically over-parameterized, bringing considerable computational overhead and memory footprint in inference. Pruning a proportion of unimportant filters is an efficient way to mitigate the inference cost. For this purpose, identifying unimportant convolutional filters is the key to effective filter pruning. Previous work prunes filters according to either their weight norms or the corresponding batch-norm scaling factors, while neglecting the sequential dependency between adjacent layers. In this paper, we further develop the norm-based importance esti…
Structured Pruning for Deep Convolutional Neural Networks: A survey
Centre for Frontier AI Research (CFAR), Agency for Science Technology and Research (A*STAR)（新加坡科技研究局前沿人工智能研究中心）；Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局高性能计算研究所）
In order to deploy deep convolutional neural networks (CNNs) on resource-limited devices, many model pruning methods for filters and weights have been developed, while only a few to layer pruning. However, compared with filter pruning and weight pruning, the compact model obtained by layer pruning has less inference time and run-time memory usage when the same FLOPs and number of parameters are pruned because of less data moving in memory. In this paper, we propose a simple layer pruning method using fusible residual convolutional block (ResConv), which is implemented by inserting shortcut con…
Recent works imply that the channel pruning can be regarded as searching optimal sub-structure from unpruned networks. However, existing works based on this observation require training and evaluating a large number of structures, which limits their application. In this paper, we propose a novel differentiable method for channel pruning, named Differentiable Markov Channel Pruning (DMCP), to efficiently search the optimal sub-structure. Our method is differentiable and can be directly optimized by gradient descent with respect to standard task loss and budget regularization (e.g. FLOPs constra…
The convolutional neural network has achieved great success in fulfilling computer vision tasks despite large computation overhead against efficient deployment. Structured (channel) pruning is usually applied to reduce the model redundancy while preserving the network structure, such that the pruned network can be easily deployed in practice. However, existing structured pruning methods require hand-crafted rules which may lead to tremendous pruning space. In this paper, we introduce Differentiable Annealing Indicator Search (DAIS) that leverages the strength of neural architecture search in t…
The success of convolutional neural networks (CNNs) in computer vision applications has been accompanied by a significant increase of computation and memory costs, which prohibits its usage on resource-limited environments such as mobile or embedded devices. To this end, the research of CNN compression has recently become emerging. In this paper, we propose a novel filter pruning scheme, termed structured sparsity regularization (SSR), to simultaneously speedup the computation and reduce the memory overhead of CNNs, which can be well supported by various off-the-shelf deep learning libraries. …
Channel pruning is among the predominant approaches to compress deep neural networks. To this end, most existing pruning methods focus on selecting channels (filters) by importance/optimization or regularization based on rule-of-thumb designs, which defects in sub-optimal pruning. In this paper, we propose a new channel pruning method based on artificial bee colony algorithm (ABC), dubbed as ABCPruner, which aims to efficiently find optimal pruned structure, i.e., channel number in each layer, rather than selecting "important" channels as previous works did. To solve the intractably huge combi…
Depthwise separable convolutions and frequency-domain convolutions are two recent ideas for building efficient convolutional neural networks. They are seemingly incompatible: the vast majority of operations in depthwise separable CNNs are in pointwise convolutional layers, but pointwise layers use 1x1 kernels, which do not benefit from frequency transformation. This paper unifies these two ideas by transforming the activations, not the kernels. Our key insights are that 1) pointwise convolutions commute with frequency transformation and thus can be computed in the frequency domain without modi…
Filter Pruning For CNN With Enhanced Linear Representation Redundancy
Tianjin Normal University（天津师范大学）；Southwestern University of Finance and Economics（西南财经大学）；University of Electronic Science and Technology of China（电子科技大学）
Xiamen University（厦门大学）；Beihang University（北京航空航天大学）；University of Chinese Academy of Sciences（中国科学院大学）；BestImage, Tencent Technology (Shanghai) Co.,Ltd（腾讯科技（上海）有限公司贝思图）
Structured pruning of filters or neurons has received increased focus for compressing convolutional neural networks. Most existing methods rely on multi-stage optimizations in a layer-wise manner for iteratively pruning and retraining which may not be optimal and may be computation intensive. Besides, these methods are designed for pruning a specific structure, such as filter or block structures without jointly pruning heterogeneous structures. In this paper, we propose an effective structured pruning approach that jointly prunes filters as well as other structures in an end-to-end manner. To …
ETH Zürich（苏黎世联邦理工学院）；The University of Sydney（悉尼大学）；KU Leuven（鲁汶大学）
Network pruning has been the driving force for the acceleration of neural networks and the alleviation of model storage/transmission burden. With the advent of AutoML and neural architecture search (NAS), pruning has become topical with automatic mechanism and searching based architecture optimization. Yet, current automatic designs rely on either reinforcement learning or evolutionary algorithm. Due to the non-differentiability of those algorithms, the pruning algorithm needs a long searching stage before reaching the convergence. To circumvent this problem, this paper introduces a differenti…
Dropout is a well-known regularization method by sampling a sub-network from a larger deep neural network and training different sub-networks on different subsets of the data. Inspired by the dropout concept, we propose EDropout as an energy-based framework for pruning neural networks in classification tasks. In this approach, a set of binary pruning state vectors (population) represents a set of corresponding sub-networks from an arbitrary provided original neural network. An energy loss function assigns a scalar energy loss value to each pruning state. The energy-based model stochastically e…
Channel pruning is one of the predominant approaches for accelerating deep neural networks. Most existing pruning methods either train from scratch with a sparsity inducing term such as group lasso, or prune redundant channels in a pretrained network and then fine tune the network. Both strategies suffer from some limitations: the use of group lasso is computationally expensive, difficult to converge and often suffers from worse behavior due to the regularization bias. The methods that start with a pretrained network either prune channels uniformly across the layers or prune channels based on …
While vision transformers (ViTs) have continuously achieved new milestones in the field of computer vision, their sophisticated network architectures with high computation and memory costs have impeded their deployment on resource-limited edge devices. In this paper, we propose a hardware-efficient image-adaptive token pruning framework called HeatViT for efficient yet accurate ViT acceleration on embedded FPGAs. By analyzing the inherent computational patterns in ViTs, we first design an effective attention-based multi-head token selector, which can be progressively inserted before transforme…
Sensetime Research（商汤科技研究院）；Tsinghua University（清华大学）；Syracuse University（雪城大学）；Northeastern University（东北大学）；Florida International University（佛罗里达国际大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；IBM Research（IBM研究院）
Weight pruning and weight quantization are two important categories of DNN model compression. Prior work on these techniques are mainly based on heuristics. A recent work developed a systematic frame-work of DNN weight pruning using the advanced optimization technique ADMM (Alternating Direction Methods of Multipliers), achieving one of state-of-art in weight pruning results. In this work, we first extend such one-shot ADMM-based framework to guarantee solution feasibility and provide fast convergence rate, and generalize to weight quantization as well. We have further developed a multi-step, …
NVIDIA（英伟达）；University of California, Berkeley（加州大学伯克利分校）；Duke University（杜克大学）
Transformers yield state-of-the-art results across many tasks. However, their heuristically designed architecture impose huge computational costs during inference. This work aims on challenging the common design philosophy of the Vision Transformer (ViT) model with uniform dimension across all the stacked blocks in a model stage, where we redistribute the parameters both across transformer blocks and between different structures within the block via the first systematic attempt on global structural pruning. Dealing with diverse ViT structural components, we derive a novel Hessian-based structu…
Zhejiang University（浙江大学）；Fabu Inc.（法布公司）；Alibaba-Zhejiang University Joint Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）；GAC R&D Center（广汽研究院）
Neural network compression empowers the effective yet unwieldy deep convolutional neural networks (CNN) to be deployed in resource-constrained scenarios. Most state-of-the-art approaches prune the model in filter-level according to the "importance" of filters. Despite their success, we notice they suffer from at least two of the following problems: 1) The redundancy among filters is not considered because the importance is evaluated independently. 2) Cross-layer filter comparison is unachievable since the importance is defined locally within each layer. Consequently, we must manually specify l…
Nanjing University（南京大学）；University of California, Berkeley（加州大学伯克利分校）；Peking University（北京大学）
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 precision of each layer remains challenging. Previous attempts on bit-level regularization and pruning-based dynamic precision adjustment during training suffer from noisy gradients and unstable convergence. In this work, we propose Continuous Sparsification Quantization (CSQ), a bit-level training method to search for mixed-precision quantization schemes with improved stability. …
Deep neural networks (DNN) are prone to miscalibrated predictions, often exhibiting a mismatch between the predicted output and the associated confidence scores. Contemporary model calibration techniques mitigate the problem of overconfident predictions by pushing down the confidence of the winning class while increasing the confidence of the remaining classes across all test samples. However, from a deployment perspective, an ideal model is desired to (i) generate well-calibrated predictions for high-confidence samples with predicted probability say >0.95, and (ii) generate a higher proportio…
Pruning is a well-known mechanism for reducing the computational cost of deep convolutional networks. However, studies have shown the potential of pruning as a form of regularization, which reduces overfitting and improves generalization. We demonstrate that this family of strategies provides additional benefits beyond computational performance and generalization. Our analyses reveal that pruning structures (filters and/or layers) from convolutional networks increase not only generalization but also robustness to adversarial images (natural images with content modified). Such achievements are …
The pressing need to reduce the capacity of deep neural networks has stimulated the development of network dilution methods and their analysis. While the ability of $L_1$ and $L_0$ regularization to encourage sparsity is often mentioned, $L_2$ regularization is seldom discussed in this context. We present a novel framework for weight pruning by sampling from a probability function that favors the zeroing of smaller weights. In addition, we examine the contribution of $L_1$ and $L_2$ regularization to the dynamics of node pruning while optimizing for weight pruning. We then demonstrate the effe…
Factorized layers--operations parameterized by products of two or more matrices--occur in a variety of deep learning contexts, including compressed model training, certain types of knowledge distillation, and multi-head self-attention architectures. We study how to initialize and regularize deep nets containing such layers, examining two simple, understudied schemes, spectral initialization and Frobenius decay, for improving their performance. The guiding insight is to design optimization routines for these networks that are as close as possible to that of their well-tuned, non-decomposed coun…
Pruning is a model compression method that removes redundant parameters in deep neural networks (DNNs) while maintaining accuracy. Most available filter pruning methods require complex treatments such as iterative pruning, features statistics/ranking, or additional optimization designs in the training process. In this paper, we propose a simple and effective regularization strategy from a new perspective of evolution of features, which we call feature flow regularization (FFR), for improving structured sparsity and filter pruning in DNNs. Specifically, FFR imposes controls on the gradient and …
Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；University of Sydney（悉尼大学）
Exploring deep convolutional neural networks of high efficiency and low memory usage is very essential for a wide variety of machine learning tasks. Most of existing approaches used to accelerate deep models by manipulating parameters or filters without data, e.g., pruning and decomposition. In contrast, we study this problem from a different perspective by respecting the difference between data. An instance-wise feature pruning is developed by identifying informative features for different instances. Specifically, by investigating a feature decay regularization, we expect intermediate feature…
Alternating Gradient Flow Utility: A Unified Metric for Structural Pruning and Dynamic Routing in Deep Networks
School of Mathematics, Southeast University（东南大学数学学院）；Systems Research Institute of the Polish Academy of Sciences（波兰科学院系统研究所）；School of Cyber Science & Engineering, Southeast University（东南大学网络科学与工程学院）；Institute of Computer Science, AGH University of Krakow（克拉科夫AGH大学计算机科学学院）；SAN University（SAN大学）
Syracuse University（雪城大学）；Northeastern University（东北大学）；University of Connecticut（康涅狄格大学）；Alibaba Group（阿里巴巴集团）
To address the large model size and intensive computation requirement of deep neural networks (DNNs), weight pruning techniques have been proposed and generally fall into two categories, i.e., static regularization-based pruning and dynamic regularization-based pruning. However, the former method currently suffers either complex workloads or accuracy degradation, while the latter one takes a long time to tune the parameters to achieve the desired pruning rate without accuracy loss. In this paper, we propose a unified DNN weight pruning framework with dynamically updated regularization terms bo…
Beijing University of Posts and Telecommunications（北京邮电大学）；EBUPT Information Technology Co., Ltd.（亿阳信通股份有限公司）
Channel pruning can significantly accelerate and compress deep neural networks. Many channel pruning works utilize structured sparsity regularization to zero out all the weights in some channels and automatically obtain structure-sparse network in training stage. However, these methods apply structured sparsity regularization on each layer separately where the correlations between consecutive layers are omitted. In this paper, we first combine one out-channel in current layer and the corresponding in-channel in next layer as a regularization group, namely out-in-channel. Our proposed Out-In-Ch…
The large amount of memory bandwidth between local buffer and external DRAM has become the speedup bottleneck of CNN hardware accelerators, especially for activation maps. To reduce memory bandwidth, we propose to learn pruning unimportant blocks dynamically with zero block regularization of activation maps (Zebra). This strategy has low computational overhead and could easily integrate with other pruning methods for better performance. The experimental results show that the proposed method can reduce 70\% of memory bandwidth for Resnet-18 on Tiny-Imagenet within 1\% accuracy drops and 2\% acc…
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 backward pass is performed with high-precision weights while quantized low-precision weights and activations are used in the forward pass to calculate the loss function for training. Thus, the gradient descent becomes suboptimal, and accuracy loss follows. In order to reduce the mismatch in the forward and backward passes, we utilize mean squared quantization error (MSQE) regularizat…
Northeastern University（东北大学）；Syracuse University（雪城大学）；SUNY University at Buffalo（纽约州立大学布法罗分校）；University of Southern California（南加利福尼亚大学）
To facilitate efficient embedded and hardware implementations of deep neural networks (DNNs), two important categories of DNN model compression techniques: weight pruning and weight quantization are investigated. The former leverages the redundancy in the number of weights, whereas the latter leverages the redundancy in bit representation of weights. However, there lacks a systematic framework of joint weight pruning and quantization of DNNs, thereby limiting the available model compression ratio. Moreover, the computation reduction, energy efficiency improvement, and hardware performance over…
The University of Sydney（悉尼大学）；SenseTime（商汤科技）；Tsinghua University（清华大学）；Tianjin University（天津大学）；Institute for Artificial Intelligence, Tsinghua University (THUAI)（清华大学人工智能研究院）；Beijing National Research Center for Information Science and Technology (BNRist)（北京信息科学与技术国家研究中心）
To deploy a well-trained CNN model on low-end computation edge devices, it is usually supposed to compress or prune the model under certain computation budget (e.g., FLOPs). Current filter pruning methods mainly leverage feature maps to generate important scores for filters and prune those with smaller scores, which ignores the variance of input batches to the difference in sparse structure over filters. In this paper, we propose a data agnostic filter pruning method that uses an auxiliary network named Dagger module to induce pruning and takes pretrained weights as input to learn the importan…
School of Electrical and Information Engineering, The University of Sydney（悉尼大学电气与信息工程学院）；Xilinx Research Labs（赛灵思研究实验室）
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 u…
