In convolutional neural networks (CNNs), the filter grouping in convolution layers is known to be useful to reduce the network parameter size. In this paper, we propose a new logarithmic filter grouping which can capture the nonlinearity of filter distribution in CNNs. The proposed logarithmic filter grouping is installed in shallow CNNs applicable in a mobile application. Experiments were performed with the shallow CNNs for classification tasks. Our classification results on Multi-PIE dataset for facial expression recognition and CIFAR-10 dataset for object classification reveal that the compact CNN with the proposed logarithmic filter grouping scheme outperforms the same network with the uniform filter grouping in terms of accuracy and parameter efficiency. Our results indicate that the efficiency of shallow CNNs can be improved by the proposed logarithmic filter grouping.
University of South Australia（南澳大学）；Institute for Telecommunications Research（电信研究所）；School of Information Technology and Mathematical Sciences（信息技术与数学科学学院）
We present a neural network architecture and training method designed to enable very rapid training and low implementation complexity. Due to its training speed and very few tunable parameters, the method has strong potential for applications requiring frequent retraining or online training. The approach is characterized by (a) convolutional filters based on biologically inspired visual processing filters, (b) randomly-valued classifier-stage input weights, (c) use of least squares regression to train the classifier output weights in a single batch, and (d) linear classifier-stage output units…
Prairie View A&M University, Texas A&M University System（德克萨斯农工大学系统普雷里维尤农工大学）
In this paper, we address the issue of how to enhance the generalization performance of convolutional neural networks (CNN) in the early learning stage for image classification. This is motivated by real-time applications that require the generalization performance of CNN to be satisfactory within limited training time. In order to achieve this, a novel hierarchical transfer CNN framework is proposed. It consists of a group of shallow CNNs and a cloud CNN, where the shallow CNNs are trained firstly and then the first layers of the trained shallow CNNs are used to initialize the first layer of …
Duke University（杜克大学）；Universidad de la República（共和国大学）；Technion-Israel Institute of Technology（以色列理工学院）
Hash codes are efficient data representations for coping with the ever growing amounts of data. In this paper, we introduce a random forest semantic hashing scheme that embeds tiny convolutional neural networks (CNN) into shallow random forests, with near-optimal information-theoretic code aggregation among trees. We start with a simple hashing scheme, where random trees in a forest act as hashing functions by setting `1' for the visited tree leaf, and `0' for the rest. We show that traditional random forests fail to generate hashes that preserve the underlying similarity between the trees, re…
Facial expressions recognition (FER) of 3D face scans has received a significant amount of attention in recent years. Most of the facial expression recognition methods have been proposed using mainly 2D images. These methods suffer from several issues like illumination changes and pose variations. Moreover, 2D mapping from 3D images may lack some geometric and topological characteristics of the face. Hence, to overcome this problem, a multi-modal 2D + 3D feature-based method is proposed. We extract shallow features from the 3D images, and deep features using Convolutional Neural Networks (CNN)…
Indian Institute of Information Technology Sri City（斯里城印度信息技术学院）
The Convolutional Neural Networks (CNNs), in domains like computer vision, mostly reduced the need for handcrafted features due to its ability to learn the problem-specific features from the raw input data. However, the selection of dataset-specific CNN architecture, which mostly performed by either experience or expertise is a time-consuming and error-prone process. To automate the process of learning a CNN architecture, this paper attempts at finding the relationship between Fully Connected (FC) layers with some of the characteristics of the datasets. The CNN architectures, and recently data…
University of Tübingen（蒂宾根大学）；Bernstein Center for Computational Neuroscience（伯恩斯坦计算神经科学中心）；Max Planck Institute for Biological Cybernetics（马克斯·普朗克生物控制论研究所）
Here we demonstrate that the feature space of random shallow convolutional neural networks (CNNs) can serve as a surprisingly good model of natural textures. Patches from the same texture are consistently classified as being more similar then patches from different textures. Samples synthesized from the model capture spatial correlations on scales much larger then the receptive field size, and sometimes even rival or surpass the perceptual quality of state of the art texture models (but show less variability). The current state of the art in parametric texture synthesis relies on the multi-lay…
School of Computer Science, China University of Geosciences（中国地质大学计算机学院）
In the proposed SEHybridSN model, a dense block was used to reuse shallow feature and aimed at better exploiting hierarchical spatial spectral feature. Subsequent depth separable convolutional layers were used to discriminate the spatial information. Further refinement of spatial spectral features was realized by the channel attention method, which were performed behind every 3D convolutional layer and every 2D convolutional layer. Experiment results indicate that our proposed model learn more discriminative spatial spectral features using very few training data. SEHybridSN using only 0.05 and…
Tianjin University（天津大学）；Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences（中国科学院西安光学精密机械研究所）
Network in Netwrok (NiN) is an effective instance and an important extension of Convolutional Neural Network (CNN) consisting of alternating convolutional layers and pooling layers. Instead of using a linear filter for convolution, NiN utilizes shallow MultiLayer Perceptron (MLP), a nonlinear function, to replace the linear filter. Because of the powerfulness of MLP and $ 1\times 1 $ convolutions in spatial domain, NiN has stronger ability of feature representation and hence results in better recognition rate. However, MLP itself consists of fully connected layers which give rise to a large nu…
South China University of Technology（华南理工大学）；The University of Adelaide（阿德莱德大学）；Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）
Depth is one of the key factors behind the success of convolutional neural networks (CNNs). Since ResNet, we are able to train very deep CNNs as the gradient vanishing issue has been largely addressed by the introduction of skip connections. However, we observe that, when the depth is very large, the intermediate layers (especially shallow layers) may fail to receive sufficient supervision from the loss due to the severe transformation through a long backpropagation path. As a result, the representation power of intermediate layers can be very weak and the model becomes very redundant with lim…
Bangladesh University of Engineering and Technology（孟加拉国工程技术大学）
Myocardial Infarction is one of the leading causes of death worldwide. This paper presents a Convolutional Neural Network (CNN) architecture which takes raw Electrocardiography (ECG) signal from lead II, III and AVF and differentiates between inferior myocardial infarction (IMI) and healthy signals. The performance of the model is evaluated on IMI and healthy signals obtained from Physikalisch-Technische Bundesanstalt (PTB) database. A subject-oriented approach is taken to comprehend the generalization capability of the model and compared with the current state of the art. In a subject-oriente…
Single Shot MultiBox Detector (SSD) is one of the fastest algorithms in the current object detection field, which uses fully convolutional neural network to detect all scaled objects in an image. Deconvolutional Single Shot Detector (DSSD) is an approach which introduces more context information by adding the deconvolution module to SSD. And the mean Average Precision (mAP) of DSSD on PASCAL VOC2007 is improved from SSD's 77.5% to 78.6%. Although DSSD obtains higher mAP than SSD by 1.1%, the frames per second (FPS) decreases from 46 to 11.8. In this paper, we propose a single stage end-to-end …
Larger networks generally have greater representational power at the cost of increased computational complexity. Sparsifying such networks has been an active area of research but has been generally limited to static regularization or dynamic approaches using reinforcement learning. We explore a mixture of experts (MoE) approach to deep dynamic routing, which activates certain experts in the network on a per-example basis. Our novel DeepMoE architecture increases the representational power of standard convolutional networks by adaptively sparsifying and recalibrating channel-wise features in ea…
One impressive advantage of convolutional neural networks (CNNs) is their ability to automatically learn feature representation from raw pixels, eliminating the need for hand-designed procedures. However, recent methods for single image super-resolution (SR) fail to maintain this advantage. They utilize CNNs in two decoupled steps, i.e., first upsampling the low resolution (LR) image to the high resolution (HR) size with hand-designed techniques (e.g., bicubic interpolation), and then applying CNNs on the upsampled LR image to reconstruct HR results. In this paper, we seek an alternative and p…
We present a method for learning discriminative filters using a shallow Convolutional Neural Network (CNN). We encode rotation invariance directly in the model by tying the weights of groups of filters to several rotated versions of the canonical filter in the group. These filters can be used to extract rotation invariant features well-suited for image classification. We test this learning procedure on a texture classification benchmark, where the orientations of the training images differ from those of the test images. We obtain results comparable to the state-of-the-art. Compared to standard…
Government College of Engineering & Ceramic Technology（政府工程与陶瓷技术学院）；Indian Institute of Science Education and Research (IISER)（印度科学教育与研究学院）
The advent of Deep Learning models like VGG-16 and Resnet-50 has considerably revolutionized the field of image classification, and by using these Convolutional Neural Networks (CNN) architectures, one can get a high classification accuracy on a wide variety of image datasets. However, these Deep Learning models have a very high computational complexity and so incur a high computational cost of running these algorithms as well as make it hard to interpret the results. In this paper, we present a shallow CNN architecture which gives the same classification accuracy as the VGG-16 and Resnet-50 m…
The latest generation of Convolutional Neural Networks (CNN) have achieved impressive results in challenging benchmarks on image recognition and object detection, significantly raising the interest of the community in these methods. Nevertheless, it is still unclear how different CNN methods compare with each other and with previous state-of-the-art shallow representations such as the Bag-of-Visual-Words and the Improved Fisher Vector. This paper conducts a rigorous evaluation of these new techniques, exploring different deep architectures and comparing them on a common ground, identifying and…
Graph convolution networks have recently garnered a lot of attention for representation learning on non-Euclidean feature spaces. Recent research has focused on stacking multiple layers like in convolutional neural networks for the increased expressive power of graph convolution networks. However, simply stacking multiple graph convolution layers lead to issues like vanishing gradient, over-fitting and over-smoothing. Such problems are much less when using shallower networks, even though the shallow networks have lower expressive power. In this work, we propose a novel Multipath Graph convolut…
Universitat Politecnica de Catalunya（加泰罗尼亚理工大学）；Insight Center for Data Analytics（洞察数据分析中心）；Dublin City University（都柏林城市大学）
The prediction of salient areas in images has been traditionally addressed with hand-crafted features based on neuroscience principles. This paper, however, addresses the problem with a completely data-driven approach by training a convolutional neural network (convnet). The learning process is formulated as a minimization of a loss function that measures the Euclidean distance of the predicted saliency map with the provided ground truth. The recent publication of large datasets of saliency prediction has provided enough data to train end-to-end architectures that are both fast and accurate. T…
We present a logarithmic-scale efficient convolutional neural network architecture for edge devices, named WaveletNet. Our model is based on the well-known depthwise convolution, and on two new layers, which we introduce in this work: a wavelet convolution and a depthwise fast wavelet transform. By breaking the symmetry in channel dimensions and applying a fast algorithm, WaveletNet shrinks the complexity of convolutional blocks by an O(logD/D) factor, where D is the number of channels. Experiments on CIFAR-10 and ImageNet classification show superior and comparable performances of WaveletNet …
Northwestern Polytechnical University（西北工业大学）；Australian National University（澳大利亚国立大学）；NICTA（澳大利亚国家信息通信技术卓越中心）
Deep convolutional neural network (CNN) based salient object detection methods have achieved state-of-the-art performance and outperform those unsupervised methods with a wide margin. In this paper, we propose to integrate deep and unsupervised saliency for salient object detection under a unified framework. Specifically, our method takes results of unsupervised saliency (Robust Background Detection, RBD) and normalized color images as inputs, and directly learns an end-to-end mapping between inputs and the corresponding saliency maps. The color images are fed into a Fully Convolutional Neural…
Nowadays most research in visual recognition using Convolutional Neural Networks (CNNs) follows the "deeper model with deeper confidence" belief to gain a higher recognition accuracy. At the same time, deeper model brings heavier computation. On the other hand, for a large chunk of recognition challenges, a system can classify images correctly using simple models or so-called shallow networks. Moreover, the implementation of CNNs faces with the size, weight, and energy constraints on the embedded devices. In this paper, we implement the adaptive switching between shallow and deep networks to r…
Image forgery detection is the task of detecting and localizing forged parts in tampered images. Previous works mostly focus on high resolution images using traces of resampling features, demosaicing features or sharpness of edges. However, a good detection method should also be applicable to low resolution images because compressed or resized images are common these days. To this end, we propose a Shallow Convolutional Neural Network(SCNN), capable of distinguishing the boundaries of forged regions from original edges in low resolution images. SCNN is designed to utilize the information of ch…
Georgia Institute of Technology（佐治亚理工学院）；DeepSig Inc.（DeepSig公司）
I/Q modulation classification is a unique pattern recognition problem as the data for each class varies in quality, quantified by signal to noise ratio (SNR), and has structure in the complex-plane. Previous work shows treating these samples as complex-valued signals and computing complex-valued convolutions within deep learning frameworks significantly increases the performance over comparable shallow CNN architectures. In this work, we claim state of the art performance by enabling high-capacity architectures containing residual and/or dense connections to compute complex-valued convolutions…
Feature representations, both hand-designed and learned ones, are often hard to analyze and interpret, even when they are extracted from visual data. We propose a new approach to study image representations by inverting them with an up-convolutional neural network. We apply the method to shallow representations (HOG, SIFT, LBP), as well as to deep networks. For shallow representations our approach provides significantly better reconstructions than existing methods, revealing that there is surprisingly rich information contained in these features. Inverting a deep network trained on ImageNet pr…
The recent advances in deep learning indicate significant progress in the field of single image super-resolution. With the advent of these techniques, high-resolution image with high peak signal to noise ratio (PSNR) and excellent perceptual quality can be reconstructed. The major challenges associated with existing deep convolutional neural networks are their computational complexity and time; the increasing depth of the networks, often result in high space complexity. To alleviate these issues, we developed an innovative shallow residual feature representative network (SRFRN) that uses a bic…
Understanding how the visual cortex of the human brain really works is still an open problem for science today. A better understanding of natural intelligence could also benefit object-recognition algorithms based on convolutional neural networks. In this paper we demonstrate the asset of using a shallow residual neural network for this task. The benefit of this approach is that earlier stages of the network can be accurately trained, which allows us to add more layers at the earlier stage. With this additional layer the prediction of the visual brain activity improves from $10.4\%$ (block 1) …
Australian Centre for Field Robotics（澳大利亚野外机器人中心）；Computing and Audio Research Laboratory（计算与音频研究实验室）；The University of Sydney（悉尼大学）
The propagation of sound in a shallow water environment is characterized by boundary reflections from the sea surface and sea floor. These reflections result in multiple (indirect) sound propagation paths, which can degrade the performance of passive sound source localization methods. This paper proposes the use of convolutional neural networks (CNNs) for the localization of sources of broadband acoustic radiated noise (such as motor vessels) in shallow water multipath environments. It is shown that CNNs operating on cepstrogram and generalized cross-correlogram inputs are able to more reliabl…
Stanford University（斯坦福大学）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
We present Caffe con Troll (CcT), a fully compatible end-to-end version of the popular framework Caffe with rebuilt internals. We built CcT to examine the performance characteristics of training and deploying general-purpose convolutional neural networks across different hardware architectures. We find that, by employing standard batching optimizations for CPU training, we achieve a 4.5x throughput improvement over Caffe on popular networks like CaffeNet. Moreover, with these improvements, the end-to-end training time for CNNs is directly proportional to the FLOPS delivered by the CPU, which e…
National Technical University of Athens（雅典国立技术大学）；National and Kapodistrian University of Athens（雅典国立卡波迪斯特里安大学）；Aretaieion Hospital（阿雷泰翁医院）
Deep Convolutional Neural Networks (CNNs) for image classification successively alternate convolutions and downsampling operations, such as pooling layers or strided convolutions, resulting in lower resolution features the deeper the network gets. These downsampling operations save computational resources and provide some translational invariance as well as a bigger receptive field at the next layers. However, an inherent side-effect of this is that high-level features, produced at the deep end of the network, are always captured in low resolution feature maps. The inverse is also true, as sha…
Tensor-Augmented Convolutional Neural Networks: Enhancing Expressivity with Generic Tensor Kernels
blueqat Inc.（blueqat公司）；Center for Quantum Science and Engineering, National Taiwan University（国立台湾大学量子科学与工程中心）；Graduate School of Science and Technology, Keio University（庆应义塾大学理工学研究科）；Keio University Sustainable Quantum Artificial Intelligence Center (KSQAIC)（庆应义塾大学可持续量子人工智能中心）
EuroMov Digital Health in Motion（EuroMov运动数字健康机构）；Univ. Montpellier（蒙彼利埃大学）；IMT Mines Ales（法国国立高等矿业电信学校联盟阿莱斯矿业学院）
In recent years, neuroscientists have been interested to the development of brain-computer interface (BCI) devices. Patients with motor disorders may benefit from BCIs as a means of communication and for the restoration of motor functions. Electroencephalography (EEG) is one of most used for evaluating the neuronal activity. In many computer vision applications, deep neural networks (DNN) show significant advantages. Towards to ultimate usage of DNN, we present here a shallow neural network that uses mainly two convolutional neural network (CNN) layers, with relatively few parameters and fast …
Coventry University（考文垂大学）；University of Auckland（奥克兰大学）；Warshel Institute for Computational Biology（瓦谢尔计算生物学研究所）；The Chinese University of Hong Kong, Shenzhen (CUHK-SZ)（香港中文大学（深圳））；Centro Studi Eteropoiesi（埃特罗波耶西研究中心）
This paper presents the 'hyper-sinh', a variation of the m-arcsinh activation function suitable for Deep Learning (DL)-based algorithms for supervised learning, such as Convolutional Neural Networks (CNN). hyper-sinh, developed in the open source Python libraries TensorFlow and Keras, is thus described and validated as an accurate and reliable activation function for both shallow and deep neural networks. Improvements in accuracy and reliability in image and text classification tasks on five (N = 5) benchmark data sets available from Keras are discussed. Experimental results demonstrate the ov…
University of Toronto（多伦多大学）；The Hospital for Sick Children（病童医院）
Many high-performance classification models utilize complex CNN-based architectures for Alzheimer's Disease classification. We aim to investigate two relevant questions regarding classification of Alzheimer's Disease using MRI: "Do Vision Transformer-based models perform better than CNN-based models?" and "Is it possible to use a shallow 3D CNN-based model to obtain satisfying results?" To achieve these goals, we propose two models that can take in and process 3D MRI scans: Convolutional Voxel Vision Transformer (CVVT) architecture, and ConvNet3D-4, a shallow 4-block 3D CNN-based model. Our re…
National University of Singapore（新加坡国立大学）；Interactive Digital Media Institute（互动数字媒体研究所）
In this paper, a robust visual tracking approach via mixed model based convolutional neural networks (SDT) is developed. In order to handle abrupt or fast motion, a prior map is generated to facilitate the localization of region of interest (ROI) before the deep tracker is performed. A top-down saliency model with nineteen shallow cues are employed to construct the prior map with online learnt combination weights. Moreover, apart from a holistic deep learner, four local networks are also trained to learn different components of the target. The generated four local heat maps will facilitate to …
Exploring Deep-to-Shallow Transformable Neural Networks for Intelligent Embedded Systems
School of Computer Science and Engineering, Southeast University (SEU)（东南大学计算机科学与工程学院）；College of Computing and Data Science, Nanyang Technological University (NTU)（南洋理工大学计算机科学与数据科学学院）
University of South Australia（南澳大学）；The University of Western Sydney（西悉尼大学）
Recent advances in training deep (multi-layer) architectures have inspired a renaissance in neural network use. For example, deep convolutional networks are becoming the default option for difficult tasks on large datasets, such as image and speech recognition. However, here we show that error rates below 1% on the MNIST handwritten digit benchmark can be replicated with shallow non-convolutional neural networks. This is achieved by training such networks using the 'Extreme Learning Machine' (ELM) approach, which also enables a very rapid training time (~10 minutes). Adding distortions, as is …
This work tackles the issue of noise removal from images, focusing on the well-known DCT image denoising algorithm. The latter, stemming from signal processing, has been well studied over the years. Though very simple, it is still used in crucial parts of state-of-the-art "traditional" denoising algorithms such as BM3D. Since a few years however, deep convolutional neural networks (CNN) have outperformed their traditional counterparts, making signal processing methods less attractive. In this paper, we demonstrate that a DCT denoiser can be seen as a shallow CNN and thereby its original linear…
