Convolutional Neural Networks (CNNs) are computationally intensive, which limits their application on mobile devices. Their energy is dominated by the number of multiplies needed to perform the convolutions. Winograd's minimal filtering algorithm (Lavin, 2015) and network pruning (Han et al., 2015) can reduce the operation count, but these two methods cannot be directly combined $-$ applying the Winograd transform fills in the sparsity in both the weights and the activations. We propose two modifications to Winograd-based CNNs to enable these methods to exploit sparsity. First, we move the ReLU operation into the Winograd domain to increase the sparsity of the transformed activations. Second, we prune the weights in the Winograd domain to exploit static weight sparsity. For models on CIFAR-10, CIFAR-100 and ImageNet datasets, our method reduces the number of multiplications by $10.4\times$, $6.8\times$ and $10.8\times$ respectively with loss of accuracy less than $0.1\%$, outperforming previous baselines by $2.0\times$-$3.0\times$. We also show that moving ReLU to the Winograd domain allows more aggressive pruning.
Deep convolutional neural networks (CNNs) are deployed in various applications but demand immense computational requirements. Pruning techniques and Winograd convolution are two typical methods to reduce the CNN computation. However, they cannot be directly combined because Winograd transformation fills in the sparsity resulting from pruning. Li et al. (2017) propose sparse Winograd convolution in which weights are directly pruned in the Winograd domain, but this technique is not very practical because Winograd-domain retraining requires low learning rates and hence significantly longer traini…
We consider the optimization of deep convolutional neural networks (CNNs) such that they provide good performance while having reduced complexity if deployed on either conventional systems with spatial-domain convolution or lower-complexity systems designed for Winograd convolution. The proposed framework produces one compressed model whose convolutional filters can be made sparse either in the spatial domain or in the Winograd domain. Hence, the compressed model can be deployed universally on any platform, without need for re-training on the deployed platform. To get a better compression rati…
Sparse methods and the use of Winograd convolutions are two orthogonal approaches, each of which significantly accelerates convolution computations in modern CNNs. Sparse Winograd merges these two and thus has the potential to offer a combined performance benefit. Nevertheless, training convolution layers so that the resulting Winograd kernels are sparse has not hitherto been very successful. By introducing a Winograd layer in place of a standard convolution layer, we can learn and prune Winograd coefficients "natively" and obtain sparsity level beyond 90% with only 0.1% accuracy loss with Ale…
This paper focuses on Winograd transformation in 3D convolutional neural networks (CNNs) that are more over-parameterized compared with the 2D version. The over-increasing Winograd parameters not only exacerbate training complexity but also barricade the practical speedups due simply to the volume of element-wise products in the Winograd domain. We attempt to reduce trainable parameters by introducing a low-rank Winograd transformation, a novel training paradigm that decouples the original large tensor into two less storage-required trainable tensors, leading to a significant complexity reduct…
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）；Jilin University（吉林大学）
Accelerating deep convolutional neural networks has become an active topic and sparked an interest in academia and industry. In this paper, we propose an efficient low-precision quantized Winograd convolution algorithm, called LANCE, which combines the advantages of fast convolution and quantization techniques. By embedding linear quantization operations into the Winograd-domain, the fast convolution can be performed efficiently under low-precision computation on graphics processing units. We test neural network models with LANCE on representative image classification datasets, including SVHN,…
We consider the optimization of deep convolutional neural networks (CNNs) such that they provide good performance while having reduced complexity if deployed on either conventional systems utilizing spatial-domain convolution or lower complexity systems designed for Winograd convolution. Furthermore, we explore the universal quantization and compression of these networks. In particular, the proposed framework produces one compressed model whose convolutional filters can be made sparse either in the spatial domain or in the Winograd domain. Hence, one compressed model can be deployed universall…
University of Oxford（牛津大学）；Arm ML Research Lab（安谋机器学习研究实验室）
Lightweight architectural designs of Convolutional Neural Networks (CNNs) together with quantization have paved the way for the deployment of demanding computer vision applications on mobile devices. Parallel to this, alternative formulations to the convolution operation such as FFT, Strassen and Winograd, have been adapted for use in CNNs offering further speedups. Winograd convolutions are the fastest known algorithm for spatially small convolutions, but exploiting their full potential comes with the burden of numerical error, rendering them unusable in quantized contexts. In this work we pr…
NVIDIA（英伟达）；Massachusetts Institute of Technology（麻省理工学院）；UC-Berkeley（加州大学伯克利分校）；Stanford University（斯坦福大学）
Convolutional Neural Networks (CNNs) have emerged as a fundamental technology for machine learning. High performance and extreme energy efficiency are critical for deployments of CNNs in a wide range of situations, especially mobile platforms such as autonomous vehicles, cameras, and electronic personal assistants. This paper introduces the Sparse CNN (SCNN) accelerator architecture, which improves performance and energy efficiency by exploiting the zero-valued weights that stem from network pruning during training and zero-valued activations that arise from the common ReLU operator applied du…
School of Computer Science and Statistics（计算机科学与统计学学院）；Lero, Trinity College Dublin（都柏林圣三一学院Lero（爱尔兰国家软件与计算机科学研究所））
Convolutional neural networks (CNNs) have dramatically improved the accuracy of tasks such as object recognition, image segmentation and interactive speech systems. CNNs require large amounts of computing resources because ofcomputationally intensive convolution layers. Fast convolution algorithms such as Winograd convolution can greatly reduce the computational cost of these layers at a cost of poor numeric properties, such that greater savings in computation exponentially increase floating point errors. A defining feature of each Winograd convolution algorithm is a set of real-value points w…
Syed Babar Ali School of Science and Engineering (SBASSE), Lahore University of Management Sciences (LUMS)（拉合尔管理科学大学赛义德·巴巴尔·阿里理工学院（SBASSE））；Department of Electrical Engineering, Syed Babar Ali School of Science and Engineering (SBASSE), Lahore University of Management Sciences (LUMS)（拉合尔管理科学大学赛义德·巴巴尔·阿里理工学院电气工程系（SBASSE））；Lahore University of Management Sciences (LUMS)（拉合尔管理科学大学（LUMS））；Department of Electrical Engineering（电气工程系）
Convolutional Neural Networks (CNNs) have gained widespread popularity in the field of computer vision and image processing. Due to huge computational requirements of CNNs, dedicated hardware-based implementations are being explored to improve their performance. Hardware platforms such as Field Programmable Gate Arrays (FPGAs) are widely being used to design parallel architectures for this purpose. In this paper, we analyze Winograd minimal filtering or fast convolution algorithms to reduce the arithmetic complexity of convolutional layers of CNNs. We explore a complex design space to find the…
This paper presents cltorch, a hardware-agnostic backend for the Torch neural network framework. cltorch enables training of deep neural networks on GPUs from diverse hardware vendors, including AMD, NVIDIA, and Intel. cltorch contains sufficient implementation to run models such as AlexNet, VGG, Overfeat, and GoogleNet. It is written using the OpenCL language, a portable compute language, governed by the Khronos Group. cltorch is the top-ranked hardware-agnostic machine learning framework on Chintala's convnet-benchmarks page. This paper presents the technical challenges encountered whilst cr…
Convolutional sparse coding improves on the standard sparse approximation by incorporating a global shift-invariant model. The most efficient convolutional sparse coding methods are based on the alternating direction method of multipliers and the convolution theorem. The only major difference between these methods is how they approach a convolutional least-squares fitting subproblem. This letter presents a solution to this subproblem, which improves the efficiency of the state-of-the-art algorithms. We also use the same approach for developing an efficient convolutional dictionary learning met…
Convolutional network are the de-facto standard for analysing spatio-temporal data such as images, videos, 3D shapes, etc. Whilst some of this data is naturally dense (for instance, photos), many other data sources are inherently sparse. Examples include pen-strokes forming on a piece of paper, or (colored) 3D point clouds that were obtained using a LiDAR scanner or RGB-D camera. Standard "dense" implementations of convolutional networks are very inefficient when applied on such sparse data. We introduce a sparse convolutional operation tailored to processing sparse data that differs from prio…
Simultaneous sparse approximation (SSA) seeks to represent a set of dependent signals using sparse vectors with identical supports. The SSA model has been used in various signal and image processing applications involving multiple correlated input signals. In this paper, we propose algorithms for convolutional SSA (CSSA) based on the alternating direction method of multipliers. Specifically, we address the CSSA problem with different sparsity structures and the convolutional feature learning problem in multimodal data/signals based on the SSA model. We evaluate the proposed algorithms by apply…
Deep convolutional neural networks (ConvNets) of 3-dimensional kernels allow joint modeling of spatiotemporal features. These networks have improved performance of video and volumetric image analysis, but have been limited in size due to the low memory ceiling of GPU hardware. Existing CPU implementations overcome this constraint but are impractically slow. Here we extend and optimize the faster Winograd-class of convolutional algorithms to the $N$-dimensional case and specifically for CPU hardware. First, we remove the need to manually hand-craft algorithms by exploiting the relaxed constrain…
Convolutional neural networks (CNNs) perform well on problems such as handwriting recognition and image classification. However, the performance of the networks is often limited by budget and time constraints, particularly when trying to train deep networks. Motivated by the problem of online handwriting recognition, we developed a CNN for processing spatially-sparse inputs; a character drawn with a one-pixel wide pen on a high resolution grid looks like a sparse matrix. Taking advantage of the sparsity allowed us more efficiently to train and test large, deep CNNs. On the CASIA-OLHWDB1.1 data…
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 …
Peking University（北京大学）；National Tsinghua University（国立清华大学）；UC San Diego（加州大学圣地亚哥分校）
We propose an adversarial defense method that achieves state-of-the-art performance among attack-agnostic adversarial defense methods while also maintaining robustness to input resolution, scale of adversarial perturbation, and scale of dataset size. Based on convolutional sparse coding, we construct a stratified low-dimensional quasi-natural image space that faithfully approximates the natural image space while also removing adversarial perturbations. We introduce a novel Sparse Transformation Layer (STL) in between the input image and the first layer of the neural network to efficiently proj…
The Chinese University of Hong Kong（香港中文大学）；MEGVII Technology（旷视科技）；SmartMore（思谋科技）
Non-uniformed 3D sparse data, e.g., point clouds or voxels in different spatial positions, make contribution to the task of 3D object detection in different ways. Existing basic components in sparse convolutional networks (Sparse CNNs) process all sparse data, regardless of regular or submanifold sparse convolution. In this paper, we introduce two new modules to enhance the capability of Sparse CNNs, both are based on making feature sparsity learnable with position-wise importance prediction. They are focal sparse convolution (Focals Conv) and its multi-modal variant of focal sparse convolutio…
Compositional Factorization of Visual Scenes with Convolutional Sparse Coding and Resonator Networks
Redwood Center for Theoretical Neuroscience, UC Berkeley（加州大学伯克利分校红木理论神经科学中心）；Université Paris-Saclay（巴黎-萨克雷大学）；Örebro University（厄勒布鲁大学）；Research Institutes of Sweden（瑞典研究院）
Multiple instance learning (MIL) is the preferred approach for whole slide image classification. However, most MIL approaches do not exploit the interdependencies of tiles extracted from a whole slide image, which could provide valuable cues for classification. This paper presents a novel MIL approach that exploits the spatial relationship of tiles for classifying whole slide images. To do so, a sparse map is built from tiles embeddings, and is then classified by a sparse-input CNN. It obtained state-of-the-art performance over popular MIL approaches on the classification of cancer subtype inv…
In a deep neural network (DNN), the number of the parameters is usually huge to get high learning performances. For that reason, it costs a lot of memory and substantial computational resources, and also causes overfitting. It is known that some parameters are redundant and can be removed from the network without decreasing performance. Many sparse regularization criteria have been proposed to solve this problem. In a convolutional neural network (CNN), group sparse regularizations are often used to remove unnecessary subsets of the weights, such as filters or channels. When we apply a group s…
University of Toronto（多伦多大学）；University of Guelph（圭尔夫大学）
Convolutional Neural Networks (CNNs) have gained significant traction in the field of machine learning, particularly due to their high accuracy in visual recognition. Recent works have pushed the performance of GPU implementations of CNNs to significantly improve their classification and training times. With these improvements, many frameworks have become available for implementing CNNs on both CPUs and GPUs, with no support for FPGA implementations. In this work we present a modified version of the popular CNN framework Caffe, with FPGA support. This allows for classification using CNN models…
Facebook AI Research（Facebook人工智能研究院）；University of Oxford（牛津大学）
Convolutional networks are the de-facto standard for analyzing spatio-temporal data such as images, videos, and 3D shapes. Whilst some of this data is naturally dense (e.g., photos), many other data sources are inherently sparse. Examples include 3D point clouds that were obtained using a LiDAR scanner or RGB-D camera. Standard "dense" implementations of convolutional networks are very inefficient when applied on such sparse data. We introduce new sparse convolutional operations that are designed to process spatially-sparse data more efficiently, and use them to develop spatially-sparse convol…
The Queensland University of Technology（昆士兰科技大学）；Carnegie Mellon University（卡内基梅隆大学）
Sparse and convolutional constraints form a natural prior for many optimization problems that arise from physical processes. Detecting motifs in speech and musical passages, super-resolving images, compressing videos, and reconstructing harmonic motions can all leverage redundancies introduced by convolution. Solving problems involving sparse and convolutional constraints remains a difficult computational problem, however. In this paper we present an overview of convolutional sparse coding in a consistent framework. The objective involves iteratively optimizing a convolutional least-squares te…
Convolutional neural networks show outstanding results in a variety of computer vision tasks. However, a neural network architecture design usually faces a trade-off between model performance and computational/memory complexity. For some real-world applications, it is crucial to develop models, which can be fast and light enough to run on edge systems and mobile devices. However, many modern architectures that demonstrate good performance don't satisfy inference time and storage limitation requirements. Thus, arises a problem of neural network compression to obtain a smaller and faster model, …
While convolutional sparse representations enjoy a number of useful properties, they have received limited attention for image reconstruction problems. The present paper compares the performance of block-based and convolutional sparse representations in the removal of Gaussian white noise. While the usual formulation of the convolutional sparse coding problem is slightly inferior to the block-based representations in this problem, the performance of the convolutional form can be boosted beyond that of the block-based form by the inclusion of suitable penalties on the gradients of the coefficie…
Technion-Israel Institute of Technology（以色列理工学院）；Stanford University（斯坦福大学）
The recently proposed Multi-Layer Convolutional Sparse Coding (ML-CSC) model, consisting of a cascade of convolutional sparse layers, provides a new interpretation of Convolutional Neural Networks (CNNs). Under this framework, the computation of the forward pass in a CNN is equivalent to a pursuit algorithm aiming to estimate the nested sparse representation vectors -- or feature maps -- from a given input signal. Despite having served as a pivotal connection between CNNs and sparse modeling, a deeper understanding of the ML-CSC is still lacking: there are no pursuit algorithms that can serve …
We have implemented a convolutional neural network designed for processing sparse three-dimensional input data. The world we live in is three dimensional so there are a large number of potential applications including 3D object recognition and analysis of space-time objects. In the quest for efficiency, we experiment with CNNs on the 2D triangular-lattice and 3D tetrahedral-lattice.
King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学（KAUST））
Convolutional Sparse Coding (CSC) is a well-established image representation model especially suited for image restoration tasks. In this work, we extend the applicability of this model by proposing a supervised approach to convolutional sparse coding, which aims at learning discriminative dictionaries instead of purely reconstructive ones. We incorporate a supervised regularization term into the traditional unsupervised CSC objective to encourage the final dictionary elements to be discriminative. Experimental results show that using supervised convolutional learning results in two key advant…
University of Chinese Academy of Sciences（中国科学院大学）
Convolutional neural network (CNN) and its variants have led to many state-of-art results in various fields. However, a clear theoretical understanding about them is still lacking. Recently, multi-layer convolutional sparse coding (ML-CSC) has been proposed and proved to equal such simply stacked networks (plain networks). Here, we think three factors in each layer of it including the initialization, the dictionary design and the number of iterations greatly affect the performance of ML-CSC. Inspired by these considerations, we propose two novel multi-layer models--residual convolutional spars…
Pavlov Institute of Physiology RAS（俄罗斯科学院巴甫洛夫生理学研究所）；State University of Aerospace Instrumentation（国立航空航天仪器大学）
We consider convolutional neural network (CNN) ensemble learning with the objective function inspired by least action principle; it includes resource consumption component. We teach an agent to perceive images through the set of pre-trained classifiers and want the resulting dynamically configured system to unfold the computational graph with the trajectory that refers to the minimal number of operations and maximal expected accuracy. The proposed agent's architecture implicitly approximates the required classifier selection function with the help of reinforcement learning. Our experimental re…
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Tsinghua-Berkeley Shenzhen Institute (TBSI), Tsinghua University（清华大学清华-伯克利深圳学院）；Harvard University（哈佛大学）；University of California, Berkeley（加州大学伯克利分校）；Ohio State University（俄亥俄州立大学）
Despite strong empirical performance for image classification, deep neural networks are often regarded as ``black boxes'' and they are difficult to interpret. On the other hand, sparse convolutional models, which assume that a signal can be expressed by a linear combination of a few elements from a convolutional dictionary, are powerful tools for analyzing natural images with good theoretical interpretability and biological plausibility. However, such principled models have not demonstrated competitive performance when compared with empirically designed deep networks. This paper revisits the s…
Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）；Pontificia Universidad Católica del Perú（秘鲁天主教大学）
Two different approaches have recently been proposed for boundary handling in convolutional sparse representations, avoiding potential boundary artifacts arising from the circular boundary conditions implied by the use of frequency domain solution methods by introducing a spatial mask into the convolutional sparse coding problem. In the present paper we show that, under certain circumstances, these methods fail in their design goal of avoiding boundary artifacts. The reasons for this failure are discussed, a solution is proposed, and the practical implications are illustrated in an image deblu…
Support estimation (SE) of a sparse signal refers to finding the location indices of the non-zero elements in a sparse representation. Most of the traditional approaches dealing with SE problem are iterative algorithms based on greedy methods or optimization techniques. Indeed, a vast majority of them use sparse signal recovery techniques to obtain support sets instead of directly mapping the non-zero locations from denser measurements (e.g., Compressively Sensed Measurements). This study proposes a novel approach for learning such a mapping from a training set. To accomplish this objective, t…
Peking University（北京大学）；Bytedance Inc.（字节跳动公司）；University of Oxford（牛津大学）
We identify and overcome two key obstacles in extending the success of BERT-style pre-training, or the masked image modeling, to convolutional networks (convnets): (i) convolution operation cannot handle irregular, random-masked input images; (ii) the single-scale nature of BERT pre-training is inconsistent with convnet's hierarchical structure. For (i), we treat unmasked pixels as sparse voxels of 3D point clouds and use sparse convolution to encode. This is the first use of sparse convolution for 2D masked modeling. For (ii), we develop a hierarchical decoder to reconstruct images from multi…
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
X-ray computed tomography (CT) using sparse projection views is a recent approach to reduce the radiation dose. However, due to the insufficient projection views, an analytic reconstruction approach using the filtered back projection (FBP) produces severe streaking artifacts. Recently, deep learning approaches using large receptive field neural networks such as U-Net have demonstrated impressive performance for sparse- view CT reconstruction. However, theoretical justification is still lacking. Inspired by the recent theory of deep convolutional framelets, the main goal of this paper is, there…
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）
In this paper, we propose binary sparse convolutional networks called BSC-Net for efficient point cloud analysis. We empirically observe that sparse convolution operation causes larger quantization errors than standard convolution. However, conventional network quantization methods directly binarize the weights and activations in sparse convolution, resulting in performance drop due to the significant quantization loss. On the contrary, we search the optimal subset of convolution operation that activates the sparse convolution at various locations for quantization error alleviation, and the pe…
Deep neural networks have achieved remarkable accuracy in many artificial intelligence applications, e.g. computer vision, at the cost of a large number of parameters and high computational complexity. Weight pruning can compress DNN models by removing redundant parameters in the networks, but it brings sparsity in the weight matrix, and therefore makes the computation inefficient on GPUs. Although pruning can remove more than 80% of the weights, it actually hurts inference performance (speed) when running models on GPUs. Two major problems cause this unsatisfactory performance on GPUs. First,…
School of Electronic and Information, Wuhan University（武汉大学电子信息学院）
We propose a simple yet effective model for Single Image Super-Resolution (SISR), by combining the merits of Residual Learning and Convolutional Sparse Coding (RL-CSC). Our model is inspired by the Learned Iterative Shrinkage-Threshold Algorithm (LISTA). We extend LISTA to its convolutional version and build the main part of our model by strictly following the convolutional form, which improves the network's interpretability. Specifically, the convolutional sparse codings of input feature maps are learned in a recursive manner, and high-frequency information can be recovered from these CSCs. M…
University of Bristol（布里斯托大学）；NHS Trust Foundation（NHS信托基金会）
In representation learning, Convolutional Sparse Coding (CSC) enables unsupervised learning of features by jointly optimising both an \(\ell_2\)-norm fidelity term and a sparsity enforcing penalty. This work investigates using a regularisation term derived from an assumed Cauchy prior for the coefficients of the feature maps of a CSC generative model. The sparsity penalty term resulting from this prior is solved via its proximal operator, which is then applied iteratively, element-wise, on the coefficients of the feature maps to optimise the CSC cost function. The performance of the proposed I…
Virginia Tech（弗吉尼亚理工大学）；New Mexico Tech（新墨西哥理工学院）；Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）
Neural networks are analogous in many ways to spin glasses, systems which are known for their rich set of dynamics and equally complex phase diagrams. We apply well-known techniques in the study of spin glasses to a convolutional sparsely encoding neural network and observe power law finite-size scaling behavior in the sparsity and reconstruction error as the network denoises 32$\times$32 RGB CIFAR-10 images. This finite-size scaling indicates the presence of a continuous phase transition at a critical value of this sparsity. By using the power law scaling relations inherent to finite-size sca…
Submanifold Sparse Convolutional Networks for Automated 3D Segmentation of Kidneys and Kidney Tumours in Computed Tomography
ETH Zürich, Institute for Particle Physics and Astrophysics（苏黎世联邦理工学院，粒子物理与天体物理研究所）；University of Cambridge, Department of Physics（剑桥大学，物理系）；University of Cincinnati, Department of Physics（辛辛那提大学，物理系）；University of Cambridge, Department of Radiology（剑桥大学，放射学系）
Real-time data collection and analysis in large experimental facilities present a great challenge across multiple domains, including high energy physics, nuclear physics, and cosmology. To address this, machine learning (ML)-based methods for real-time data compression have drawn significant attention. However, unlike natural image data, such as CIFAR and ImageNet that are relatively small-sized and continuous, scientific data often come in as three-dimensional data volumes at high rates with high sparsity (many zeros) and non-Gaussian value distribution. This makes direct application of popul…
State Key Laboratory of Intelligent Technology and Systems（智能技术与系统国家重点实验室）；Tsinghua National Laboratory for Information Science and Technology（清华信息科学与技术国家实验室）；Tsinghua University（清华大学）
Nowadays, it is still difficult to adapt Convolutional Neural Network (CNN) based models for deployment on embedded devices. The heavy computation and large memory footprint of CNN models become the main burden in real application. In this paper, we propose a "Sparse Shrink" algorithm to prune an existing CNN model. By analyzing the importance of each channel via sparse reconstruction, the algorithm is able to prune redundant feature maps accordingly. The resulting pruned model thus directly saves computational resource. We have evaluated our algorithm on CIFAR-100. As shown in our experiments…
King Abdullah University of Science and Technology (KAUST)（沙特国王 Abdullah 科技大学（KAUST））
Convolutional sparse coding (CSC) is an important building block of many computer vision applications ranging from image and video compression to deep learning. We present two contributions to the state of the art in CSC. First, we significantly speed up the computation by proposing a new optimization framework that tackles the problem in the dual domain. Second, we extend the original formulation to higher dimensions in order to process a wider range of inputs, such as RGB images and videos. Our results show up to 20 times speedup compared to current state-of-the-art CSC solvers.
Traditional dictionary learning based CT reconstruction methods are patch-based and the features learned with these methods often contain shifted versions of the same features. To deal with these problems, the convolutional sparse coding (CSC) has been proposed and introduced into various applications. In this paper, inspired by the successful applications of CSC in the field of signal processing, we propose a novel sparse-view CT reconstruction method based on CSC with gradient regularization on feature maps. By directly working on whole image, which need not to divide the image into overlapp…
Neural networks, specifically deep convolutional neural networks, have achieved unprecedented performance in various computer vision tasks, but the rationale for the computations and structures of successful neural networks is not fully understood. Theories abound for the aptitude of convolutional neural networks for image classification, but less is understood about why such models would be capable of complex visual tasks such as inference and anomaly identification. Here, we propose a sparse coding interpretation of neural networks that have ReLU activation and of convolutional neural networ…
Skolkovo Institute of Science and Technology（斯科尔科沃科学技术学院）；Institute of Information Transmission Problems（信息传输问题研究所）
In this paper we present results of performance evaluation of S3DCNN - a Sparse 3D Convolutional Neural Network - on a large-scale 3D Shape benchmark ModelNet40, and measure how it is impacted by voxel resolution of input shape. We demonstrate comparable classification and retrieval performance to state-of-the-art models, but with much less computational costs in training and inference phases. We also notice that benefits of higher input resolution can be limited by an ability of a neural network to generalize high level features.
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）
Sparse voxel-based 3D convolutional neural networks (CNNs) are widely used for various 3D vision tasks. Sparse voxel-based 3D CNNs create sparse non-empty voxels from the 3D input and perform 3D convolution operations on them only. We propose a simple yet effective padding scheme --- interpolation-aware padding to pad a few empty voxels adjacent to the non-empty voxels and involve them in the 3D CNN computation so that all neighboring voxels exist when computing point-wise features via the trilinear interpolation. For fine-grained 3D vision tasks where point-wise features are essential, like s…
The most widely used form of convolutional sparse coding uses an $\ell_1$ regularization term. While this approach has been successful in a variety of applications, a limitation of the $\ell_1$ penalty is that it is homogeneous across the spatial and filter index dimensions of the sparse representation array, so that sparsity cannot be separately controlled across these dimensions. The present paper considers the consequences of replacing the $\ell_1$ penalty with a mixed group norm, motivated by recent theoretical results for convolutional sparse representations. Algorithms are developed for …
Purpose: The aim of this work is to demonstrate that convolutional neural networks (CNN) can be applied to extremely sparse image libraries by subdivision of the original image datasets. Methods: Image datasets from a conventional digital camera was created and scanning electron microscopy (SEM) measurements were obtained from the literature. The image datasets were subdivided and CNN models were trained on parts of the subdivided datasets. Results: The CNN models were capable of analyzing extremely sparse image datasets by utilizing the proposed method of image subdivision. It was furthermore…
Hong Kong University of Science and Technology University（香港科技大学）；Paradigm Inc（第四范式有限公司）；University of Macau（澳门大学）
Convolutional sparse coding (CSC) has been popularly used for the learning of shift-invariant dictionaries in image and signal processing. However, existing methods have limited scalability. In this paper, instead of convolving with a dictionary shared by all samples, we propose the use of a sample-dependent dictionary in which filters are obtained as linear combinations of a small set of base filters learned from the data. This added flexibility allows a large number of sample-dependent patterns to be captured, while the resultant model can still be efficiently learned by online learning. Ext…
Sun Yat-Sen University（中山大学）；Microsoft Research（微软研究院）；Hefei University of Technology（合肥工业大学）；University of Central Florida（中佛罗里达大学）
In this paper, we study the problem of designing efficient convolutional neural network architectures with the interest in eliminating the redundancy in convolution kernels. In addition to structured sparse kernels, low-rank kernels and the product of low-rank kernels, the product of structured sparse kernels, which is a framework for interpreting the recently-developed interleaved group convolutions (IGC) and its variants (e.g., Xception), has been attracting increasing interests. Motivated by the observation that the convolutions contained in a group convolution in IGC can be further decompo…
Simon Fraser University（西蒙菲莎大学）；University of Chicago（芝加哥大学）
We explore a key architectural aspect of deep convolutional neural networks: the pattern of internal skip connections used to aggregate outputs of earlier layers for consumption by deeper layers. Such aggregation is critical to facilitate training of very deep networks in an end-to-end manner. This is a primary reason for the widespread adoption of residual networks, which aggregate outputs via cumulative summation. While subsequent works investigate alternative aggregation operations (e.g. concatenation), we focus on an orthogonal question: which outputs to aggregate at a particular point in …
Hong Kong University of Science and Technology（香港科技大学）；University of Macau（澳门大学）
Convolutional sparse coding (CSC) improves sparse coding by learning a shift-invariant dictionary from the data. However, existing CSC algorithms operate in the batch mode and are expensive, in terms of both space and time, on large datasets. In this paper, we alleviate these problems by using online learning. The key is a reformulation of the CSC objective so that convolution can be handled easily in the frequency domain and much smaller history matrices are needed. We use the alternating direction method of multipliers (ADMM) to solve the resulting optimization problem and the ADMM subproble…
