Despite their recent success on image denoising, the need for deep and complex architectures still hinders the practical usage of CNNs. Older but computationally more efficient methods such as BM3D remain a popular choice, especially in resource-constrained scenarios. In this study, we aim to find out whether compact neural networks can learn to produce competitive results as compared to BM3D for AWGN image denoising. To this end, we configure networks with only two hidden layers and employ different neuron models and layer widths for comparing the performance with BM3D across different AWGN noise levels. Our results conclusively show that the recently proposed self-organized variant of operational neural networks based on a generative neuron model (Self-ONNs) is not only a better choice as compared to CNNs, but also provide competitive results as compared to BM3D and even significantly surpass it for high noise levels.
Tampere Universities（坦佩雷大学）；Qatar University（卡塔尔大学）
Convolutional Neural Networks (CNNs) have recently become a favored technique for image denoising due to its adaptive learning ability, especially with a deep configuration. However, their efficacy is inherently limited owing to their homogenous network formation with the unique use of linear convolution. In this study, we propose a heterogeneous network model which allows greater flexibility for embedding additional non-linearity at the core of the data transformation. To this end, we propose the idea of an operational neuron or Operational Neural Networks (ONN), which enables a flexible non-…
Discriminative learning based on convolutional neural networks (CNNs) aims to perform image restoration by learning from training examples of noisy-clean image pairs. It has become the go-to methodology for tackling image restoration and has outperformed the traditional non-local class of methods. However, the top-performing networks are generally composed of many convolutional layers and hundreds of neurons, with trainable parameters in excess of several millions. We claim that this is due to the inherent linear nature of convolution-based transformation, which is inadequate for handling seve…
Tampere University（坦佩雷大学）；Qatar University（卡塔尔大学）；HUAWEI Technologies（华为技术）
Real-world blind denoising poses a unique image restoration challenge due to the non-deterministic nature of the underlying noise distribution. Prevalent discriminative networks trained on synthetic noise models have been shown to generalize poorly to real-world noisy images. While curating real-world noisy images and improving ground truth estimation procedures remain key points of interest, a potential research direction is to explore extensions to the widely used convolutional neuron model to enable better generalization with fewer data and lower network complexity, as opposed to simply usi…
Classical image denoising methods utilize the non-local self-similarity principle to effectively recover image content from noisy images. Current state-of-the-art methods use deep convolutional neural networks (CNNs) to effectively learn the mapping from noisy to clean images. Deep denoising CNNs manifest a high learning capacity and integrate non-local information owing to the large receptive field yielded by numerous cascade of hidden layers. However, deep networks are also computationally complex and require large data for training. To address these issues, this study draws the focus on the…
Deep Convolutional Neural Networks (CNNs) have recently reached state-of-the-art Handwritten Text Recognition (HTR) performance. However, recent research has shown that typical CNNs' learning performance is limited since they are homogeneous networks with a simple (linear) neuron model. With their heterogeneous network structure incorporating non-linear neurons, Operational Neural Networks (ONNs) have recently been proposed to address this drawback. Self-ONNs are self-organized variations of ONNs with the generative neuron model that can generate any non-linear function using the Taylor approx…
In end-to-end optimized learned image compression, it is standard practice to use a convolutional variational autoencoder with generalized divisive normalization (GDN) to transform images into a latent space. Recently, Operational Neural Networks (ONNs) that learn the best non-linearity from a set of alternatives, and their self-organized variants, Self-ONNs, that approximate any non-linearity via Taylor series have been proposed to address the limitations of convolutional layers and a fixed nonlinear activation. In this paper, we propose to replace the convolutional and GDN layers in the vari…
Tampere University（坦佩雷大学）；Izmir University of Economics（伊兹密尔经济大学）；Qatar University（卡塔尔大学）；Eskişehir Osmangazi University（埃斯基谢希尔奥斯曼加齐大学）
Glaucoma leads to permanent vision disability by damaging the optical nerve that transmits visual images to the brain. The fact that glaucoma does not show any symptoms as it progresses and cannot be stopped at the later stages, makes it critical to be diagnosed in its early stages. Although various deep learning models have been applied for detecting glaucoma from digital fundus images, due to the scarcity of labeled data, their generalization performance was limited along with high computational complexity and special hardware requirements. In this study, compact Self-Organized Operational N…
Wuhan University of Science and Technology（武汉科技大学）；Nanchang Institute of Technology（南昌工程学院）
Aiming at the existing single image haze removal algorithms, which are based on prior knowledge and assumptions, subject to many limitations in practical applications, and could suffer from noise and halo amplification. An end-to-end system is proposed in this paper to reduce defects by combining the prior knowledge and deep learning method. The haze image is decomposed into the base layer and detail layers through a weighted guided image filter (WGIF) firstly, and the airlight is estimated from the base layer. Then, the base layer image is passed to the efficient deep convolutional network fo…
Is it possible to recover an image from its noisy version using convolutional neural networks? This is an interesting problem as convolutional layers are generally used as feature detectors for tasks like classification, segmentation and object detection. We present a new CNN architecture for blind image denoising which synergically combines three architecture components, a multi-scale feature extraction layer which helps in reducing the effect of noise on feature maps, an l_p regularizer which helps in selecting only the appropriate feature maps for the task of reconstruction, and finally a t…
University of Milan-Bicocca（米兰比可卡大学）；University of Pavia（帕维亚大学）
In this work we describe a Convolutional Neural Network (CNN) to accurately predict the scene illumination. Taking image patches as input, the CNN works in the spatial domain without using hand-crafted features that are employed by most previous methods. The network consists of one convolutional layer with max pooling, one fully connected layer and three output nodes. Within the network structure, feature learning and regression are integrated into one optimization process, which leads to a more effective model for estimating scene illumination. This approach achieves state-of-the-art performa…
Qatar University（卡塔尔大学）；Izmir University of Economics（伊兹密尔经济大学）；Aarhus University（奥胡斯大学）；Tampere University of Technology（坦佩雷理工大学）
Feed-forward, fully-connected Artificial Neural Networks (ANNs) or the so-called Multi-Layer Perceptrons (MLPs) are well-known universal approximators. However, their learning performance varies significantly depending on the function or the solution space that they attempt to approximate. This is mainly because of their homogenous configuration based solely on the linear neuron model. Therefore, while they learn very well those problems with a monotonous, relatively simple and linearly separable solution space, they may entirely fail to do so when the solution space is highly nonlinear and co…
We develop a novel optical neural network (ONN) framework which introduces a degree of scalar invariance to image classification estima- tion. Taking a hint from the human eye, which has higher resolution near the center of the retina, images are broken out into multiple levels of varying zoom based on a focal point. Each level is passed through an identical convolutional neural network (CNN) in a Siamese fashion, and the results are recombined to produce a high accuracy estimate of the object class. ONNs act as a wrapper around existing CNNs, and can thus be applied to many existing algorithm…
In this paper, a straightforward enhancement learning algorithm based on Separation Index (SI) concept is proposed for Convolutional Neural Networks (CNNs). At first, the SI as a supervised complexity measure is explained its usage in better learning of CNNs for classification problems illustrate. Then, a learning strategy proposes through which the first layer of a CNN is optimized by maximizing the SI, and the further layers are trained through the backpropagation algorithm to learn further layers. In order to maximize the SI at the first layer, A variant of ranking loss is optimized by usin…
Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）
Stochastic Gradient Descent (SGD) is the central workhorse for training modern CNNs. Although giving impressive empirical performance it can be slow to converge. In this paper we explore a novel strategy for training a CNN using an alternation strategy that offers substantial speedups during training. We make the following contributions: (i) replace the ReLU non-linearity within a CNN with positive hard-thresholding, (ii) reinterpret this non-linearity as a binary state vector making the entire CNN linear if the multi-layer support is known, and (iii) demonstrate that under certain conditions …
University of Waterloo（滑铁卢大学）；University of British Columbia（不列颠哥伦比亚大学）
Spiking Neural Networks (SNNs) are an emerging domain of biologically inspired neural networks that have shown promise for low-power AI. A number of methods exist for building deep SNNs, with Artificial Neural Network (ANN)-to-SNN conversion being highly successful. MaxPooling layers in Convolutional Neural Networks (CNNs) are an integral component to downsample the intermediate feature maps and introduce translational invariance, but the absence of their hardware-friendly spiking equivalents limits such CNNs' conversion to deep SNNs. In this paper, we present two hardware-friendly methods to …
In this paper we challenge the common assumption that convolutional layers in modern CNNs are translation invariant. We show that CNNs can and will exploit the absolute spatial location by learning filters that respond exclusively to particular absolute locations by exploiting image boundary effects. Because modern CNNs filters have a huge receptive field, these boundary effects operate even far from the image boundary, allowing the network to exploit absolute spatial location all over the image. We give a simple solution to remove spatial location encoding which improves translation invarianc…
Convolutional neural networks (CNNs) have yielded the excellent performance in a variety of computer vision tasks, where CNNs typically adopt a similar structure consisting of convolution layers, pooling layers and fully connected layers. In this paper, we propose to apply a novel method, namely Hybrid Orthogonal Projection and Estimation (HOPE), to CNNs in order to introduce orthogonality into the CNN structure. The HOPE model can be viewed as a hybrid model to combine feature extraction using orthogonal linear projection with mixture models. It is an effective model to extract useful informa…
Shahid Beheshti University（沙希德·贝赫什提大学）；Artificial and Natural Intelligence Toulouse Institute（图卢兹人工智能与自然智能研究所）；CNRS（法国国家科学研究中心）；Université Toulouse 3（图卢兹第三大学）
Deep convolutional neural networks (DCNNs) have become the state-of-the-art (SOTA) approach for many computer vision tasks: image classification, object detection, semantic segmentation, etc. However, most SOTA networks are too large for edge computing. Here, we suggest a simple way to reduce the number of trainable parameters and thus the memory footprint: sharing kernels between multiple convolutional layers. Kernel-sharing is only possible between ``isomorphic" layers, i.e.layers having the same kernel size, input and output channels. This is typically the case inside each stage of a DCNN. …
This paper is focused on studying the view-manifold structure in the feature spaces implied by the different layers of Convolutional Neural Networks (CNN). There are several questions that this paper aims to answer: Does the learned CNN representation achieve viewpoint invariance? How does it achieve viewpoint invariance? Is it achieved by collapsing the view manifolds, or separating them while preserving them? At which layer is view invariance achieved? How can the structure of the view manifold at each layer of a deep convolutional neural network be quantified experimentally? How does fine-t…
Saarland University（萨尔大学）；University of Tübingen（图宾根大学）
We analyze the loss landscape and expressiveness of practical deep convolutional neural networks (CNNs) with shared weights and max pooling layers. We show that such CNNs produce linearly independent features at a "wide" layer which has more neurons than the number of training samples. This condition holds e.g. for the VGG network. Furthermore, we provide for such wide CNNs necessary and sufficient conditions for global minima with zero training error. For the case where the wide layer is followed by a fully connected layer we show that almost every critical point of the empirical loss is a gl…
Convolutional Neural Networks (CNNs) have been widely applied. But as the CNNs grow, the number of arithmetic operations and memory footprint also increase. Furthermore, typical non-linear activation functions do not allow associativity of the operations encoded by consecutive layers, preventing the simplification of intermediate steps by combining them. We present a new activation function that allows associativity between sequential layers of CNNs. Even though our activation function is non-linear, it can be represented by a sequence of linear operations in the conformal model for Euclidean …
There are several effective methods in explaining the inner workings of convolutional neural networks (CNNs). However, in general, finding the inverse of the function performed by CNNs as a whole is an ill-posed problem. In this paper, we propose a method based on adjoint operators to reconstruct, given an arbitrary unit in the CNN (except for the first convolutional layer), its effective hypersurface in the input space that replicates that unit's decision surface conditioned on a particular input image. Our results show that the hypersurface reconstructed this way, when multiplied by the orig…
Convolutional neural networks (CNNs) have become the state-of-the-art tool for dealing with unsolved problems in computer vision and image processing. Since the convolution operator is a linear operator, several generalizations have been proposed to improve the performance of CNNs. One way to increase the capability of the convolution operator is by applying activation functions on the inner product operator. In this paper, we will introduce PowerLinear activation functions, which are based on the polynomial kernel generalization of the convolution operator. EvenPowLin functions are the main b…
Whereas CNNs have demonstrated immense progress in many vision problems, they suffer from a dependence on monumental amounts of labeled training data. On the other hand, dictionary learning does not scale to the size of problems that CNNs can handle, despite being very effective at low-level vision tasks such as denoising and inpainting. Recently, interest has grown in adapting dictionary learning methods for supervised tasks such as classification and inverse problems. We propose two new network layers that are based on dictionary learning: a sparse factorization layer and a convolutional spa…
Neuroimaging data, e.g. obtained from magnetic resonance imaging (MRI), is comparably homogeneous due to (1) the uniform structure of the brain and (2) additional efforts to spatially normalize the data to a standard template using linear and non-linear transformations. Convolutional neural networks (CNNs), in contrast, have been specifically designed for highly heterogeneous data, such as natural images, by sliding convolutional filters over different positions in an image. Here, we suggest a new CNN architecture that combines the idea of hierarchical abstraction in neural networks with a pri…
Humboldt Universität Berlin（柏林洪堡大学）；Freie Universität Berlin（柏林自由大学）；Charité - Universitätsmedizin Berlin（柏林夏里特医学院）
Neuroimaging studies based on magnetic resonance imaging (MRI) typically employ rigorous forms of preprocessing. Images are spatially normalized to a standard template using linear and non-linear transformations. Thus, one can assume that a patch at location (x, y, height, width) contains the same brain region across the entire data set. Most analyses applied on brain MRI using convolutional neural networks (CNNs) ignore this distinction from natural images. Here, we suggest a new layer type called patch individual filter (PIF) layer, which trains higher-level filters locally as we assume that…
The growing demand for the internet of things (IoT) makes it necessary to implement computer vision tasks such as object recognition in low-power devices. Convolutional neural networks (CNNs) are a potential approach for object recognition and detection. However, the convolutional layer in CNN consumes significant energy compared to the fully connected layers. To mitigate this problem, a new approach based on the Hadamard transformation as an alternative to the convolution operation is demonstrated using two fundamental datasets, MNIST and CIFAR10. The mathematical expression of the Hadamard m…
Convolutional layers in CNNs implement linear filters which decompose the input into different frequency bands. However, most modern architectures neglect standard principles of filter design when optimizing their model choices regarding the size and shape of the convolutional kernel. In this work, we consider the well-known problem of spectral leakage caused by windowing artifacts in filtering operations in the context of CNNs. We show that the small size of CNN kernels make them susceptible to spectral leakage, which may induce performance-degrading artifacts. To address this issue, we propo…
The University of Tokyo（东京大学）；Digital Frontier Inc.（数字前沿公司）
Texture classification is an important and challenging problem in many image processing applications. While convolutional neural networks (CNNs) achieved significant successes for image classification, texture classification remains a difficult problem since textures usually do not contain enough information regarding the shape of object. In image processing, texture classification has been traditionally studied well with spectral analyses which exploit repeated structures in many textures. Since CNNs process images as-is in the spatial domain whereas spectral analyses process images in the fr…
The pursuit algorithms integrated in multi-layer convolutional sparse coding (ML-CSC) can interpret the convolutional neural networks (CNNs). However, many current state-of-art (SOTA) pursuit algorithms require multiple iterations to optimize the solution of ML-CSC, which limits their applications to deeper CNNs due to high computational cost and large number of resources for getting very tiny gain of performance. In this study, we focus on the 0th iteration in pursuit algorithm by introducing an effective initialization strategy for each layer, by which the solution for ML-CSC can be improved…
In most computer vision applications, convolutional neural networks (CNNs) operate on dense image data generated by ordinary cameras. Designing CNNs for sparse and irregularly spaced input data is still an open problem with numerous applications in autonomous driving, robotics, and surveillance. To tackle this challenging problem, we introduce an algebraically-constrained convolution layer for CNNs with sparse input and demonstrate its capabilities for the scene depth completion task. We propose novel strategies for determining the confidence from the convolution operation and propagating it t…
Recent progress in deep convolutional neural networks (CNNs) have enabled a simple paradigm of architecture design: larger models typically achieve better accuracy. Due to this, in modern CNN architectures, it becomes more important to design models that generalize well under certain resource constraints, e.g. the number of parameters. In this paper, we propose a simple way to improve the capacity of any CNN model having large-scale features, without adding more parameters. In particular, we modify a standard convolutional layer to have a new functionality of channel-selectivity, so that the l…
Convolutional neural networks (CNN) have been more and more applied in mobile robotics such as intelligent vehicles. Security of CNNs in robotics applications is an important issue, for which potential adversarial attacks on CNNs are worth research. Pooling is a typical step of dimension reduction and information discarding in CNNs. Such information discarding may result in mis-deletion and mis-preservation of data features which largely influence the output of the network. This may aggravate the vulnerability of CNNs to adversarial attacks. In this paper, we conduct adversarial attacks on CNN…
Beihang University（北京航空航天大学）；University College London（伦敦大学学院）
Many deep Convolutional Neural Networks (CNN) make incorrect predictions on adversarial samples obtained by imperceptible perturbations of clean samples. We hypothesize that this is caused by a failure to suppress unusual signals within network layers. As remedy we propose the use of Symmetric Activation Functions (SAF) in non-linear signal transducer units. These units suppress signals of exceptional magnitude. We prove that SAF networks can perform classification tasks to arbitrary precision in a simplified situation. In practice, rather than use SAFs alone, we add them into CNNs to improve …
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
This paper presents a convolutional layer that is able to process sparse input features. As an example, for image recognition problems this allows an efficient filtering of signals that do not lie on a dense grid (like pixel position), but of more general features (such as color values). The presented algorithm makes use of the permutohedral lattice data structure. The permutohedral lattice was introduced to efficiently implement a bilateral filter, a commonly used image processing operation. Its use allows for a generalization of the convolution type found in current (spatial) convolutional n…
University of Washington（华盛顿大学）；Google Brain（谷歌大脑）
Data augmentations are important ingredients in the recipe for training robust neural networks, especially in computer vision. A fundamental question is whether neural network features encode data augmentation transformations. To answer this question, we introduce a systematic approach to investigate which layers of neural networks are the most predictive of augmentation transformations. Our approach uses features in pre-trained vision models with minimal additional processing to predict common properties transformed by augmentation (scale, aspect ratio, hue, saturation, contrast, and brightne…
Convolutional Neural Networks (CNNs) are very effective for many pattern recognition tasks. However, training deep CNNs needs extensive computation and large training data. In this paper we propose Bank of Filter-Trees (BFT) as a trans- fer learning mechanism for improving efficiency of learning CNNs. A filter-tree corresponding to a filter in k^{th} convolu- tional layer of a CNN is a subnetwork consisting of the filter along with all its connections to filters in all preceding layers. An ensemble of such filter-trees created from the k^{th} layers of many CNNs learnt on different but related…
In recent years, many publications showed that convolutional neural network based features can have a superior performance to engineered features. However, not much effort was taken so far to extract local features efficiently for a whole image. In this paper, we present an approach to compute patch-based local feature descriptors efficiently in presence of pooling and striding layers for whole images at once. Our approach is generic and can be applied to nearly all existing network architectures. This includes networks for all local feature extraction tasks like camera calibration, Patchmatch…
Visual interpretability of Convolutional Neural Networks (CNNs) has gained significant popularity because of the great challenges that CNN complexity imposes to understanding their inner workings. Although many techniques have been proposed to visualize class features of CNNs, most of them do not provide a correspondence between inputs and the extracted features in specific layers. This prevents the discovery of stimuli that each layer responds better to. We propose an approach to visually interpret CNN features given a set of images by creating corresponding images that depict the most inform…
Macquarie University（麦考瑞大学）；University of Technology Sydney（悉尼科技大学）；The University of Sydney（悉尼大学）
Automatic tumor segmentation is a crucial step in medical image analysis for computer-aided diagnosis. Although the existing methods based on convolutional neural networks (CNNs) have achieved the state-of-the-art performance, many challenges still remain in medical tumor segmentation. This is because regular CNNs can only exploit translation invariance, ignoring further inherent symmetries existing in medical images such as rotations and reflections. To mitigate this shortcoming, we propose a novel group equivariant segmentation framework by encoding those inherent symmetries for learning mor…
Wuhan University（武汉大学）；City University of Hong Kong（香港城市大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Tencent AI Lab（腾讯人工智能实验室）
In this paper, we propose a novel Convolutional Neural Network (CNN) structure for general-purpose multi-task learning (MTL), which enables automatic feature fusing at every layer from different tasks. This is in contrast with the most widely used MTL CNN structures which empirically or heuristically share features on some specific layers (e.g., share all the features except the last convolutional layer). The proposed layerwise feature fusing scheme is formulated by combining existing CNN components in a novel way, with clear mathematical interpretability as discriminative dimensionality reduc…
The convolutional layers of standard convolutional neural networks (CNNs) are equivariant to translation. However, the convolution and fully-connected layers are not equivariant or invariant to other affine geometric transformations. Recently, a new class of CNNs is proposed in which the conventional layers of CNNs are replaced with equivariant convolution, pooling, and batch-normalization layers. The final classification layer in equivariant neural networks is invariant to different affine geometric transformations such as rotation, reflection and translation, and the scalar value is obtained…
DEI, University of Padova（帕多瓦大学信息工程系）；ITC, Missouri State University（密苏里州立大学信息技术中心）
Features play a crucial role in computer vision. Initially designed to detect salient elements by means of handcrafted algorithms, features are now often learned by different layers in Convolutional Neural Networks (CNNs). This paper develops a generic computer vision system based on features extracted from trained CNNs. Multiple learned features are combined into a single structure to work on different image classification tasks. The proposed system was experimentally derived by testing several approaches for extracting features from the inner layers of CNNs and using them as inputs to SVMs t…
Optimized CNNs for Rapid 3D Point Cloud Object Recognition
Northeastern University（东北大学）；University of Pennsylvania（宾夕法尼亚大学）；Oregon State University（俄勒冈州立大学）；Carnegie Mellon University（卡内基梅隆大学）；George Washington University（乔治华盛顿大学）；Georgia Institute of Technology（佐治亚理工学院）；McGill University（麦吉尔大学）
South China Agricultural University（华南农业大学）；Pazhou Lab（琶洲实验室）
Since the Lipschitz properties of convolutional neural networks (CNNs) are widely considered to be related to adversarial robustness, we theoretically characterize the $\ell_1$ norm and $\ell_\infty$ norm of 2D multi-channel convolutional layers and provide efficient methods to compute the exact $\ell_1$ norm and $\ell_\infty$ norm. Based on our theorem, we propose a novel regularization method termed norm decay, which can effectively reduce the norms of convolutional layers and fully-connected layers. Experiments show that norm-regularization methods, including norm decay, weight decay, and s…
ADAPT Centre（ADAPT中心）；Trinity College Dublin（都柏林圣三一学院）
Convolutional neural networks (CNNs) learn filters in order to capture local correlation patterns in feature space. In contrast, in this paper we propose harmonic blocks that produce features by learning optimal combinations of spectral filters defined by the Discrete Cosine Transform. The harmonic blocks are used to replace conventional convolutional layers to construct partial or fully harmonic CNNs. We extensively validate our approach and show that the introduction of harmonic blocks into state-of-the-art CNN baseline architectures results in comparable or better performance in classificat…
Convolutional Neural Networks (CNNs) achieve impressive performance in a wide variety of fields. Their success benefited from a massive boost when very deep CNN models were able to be reliably trained. Despite their merits, CNNs fail to properly address problems with non-Euclidean data. To overcome this challenge, Graph Convolutional Networks (GCNs) build graphs to represent non-Euclidean data, borrow concepts from CNNs, and apply them in training. GCNs show promising results, but they are usually limited to very shallow models due to the vanishing gradient problem. As a result, most state-of-…
Technical University of Kaiserslautern（凯泽斯劳滕工业大学）；Technical University of Berlin（柏林工业大学）；University of Birmingham（伯明翰大学）；NPZ Innovation GmbH（NPZ创新有限公司）；University of St.Gallen（圣加仑大学）
We propose a novel training methodology -- Concept Group Learning (CGL) -- that encourages training of interpretable CNN filters by partitioning filters in each layer into concept groups, each of which is trained to learn a single visual concept. We achieve this through a novel regularization strategy that forces filters in the same group to be active in similar image regions for a given layer. We additionally use a regularizer to encourage a sparse weighting of the concept groups in each layer so that a few concept groups can have greater importance than others. We quantitatively evaluate CGL…
It is well known that Convolutional Neural Networks (CNNs) have significant redundancy in their filter weights. Various methods have been proposed in the literature to compress trained CNNs. These include techniques like pruning weights, filter quantization and representing filters in terms of a basis functions. Our approach falls in this latter class of strategies, but is distinct in that that we show both compressed learning and representation can be achieved without significant modifications of popular CNN architectures. Specifically, any convolution layer of the CNN is easily replaced by t…
University College London（伦敦大学学院）；Kings College London（伦敦国王学院）
The performance of multi-task learning in Convolutional Neural Networks (CNNs) hinges on the design of feature sharing between tasks within the architecture. The number of possible sharing patterns are combinatorial in the depth of the network and the number of tasks, and thus hand-crafting an architecture, purely based on the human intuitions of task relationships can be time-consuming and suboptimal. In this paper, we present a probabilistic approach to learning task-specific and shared representations in CNNs for multi-task learning. Specifically, we propose "stochastic filter groups'' (SFG…
Center for Research in Computer Vision（计算机视觉研究中心）；Department of Computer Science（计算机科学系）；University of Central Florida（中佛罗里达大学）
We propose an efficient and straightforward method for compressing deep convolutional neural networks (CNNs) that uses basis filters to represent the convolutional layers, and optimizes the performance of the compressed network directly in the basis space. Specifically, any spatial convolution layer of the CNN can be replaced by two successive convolution layers: the first is a set of three-dimensional orthonormal basis filters, followed by a layer of one-dimensional filters that represents the original spatial filters in the basis space. We jointly fine-tune both the basis and the filter repr…
Shenzhen University（深圳大学）；Shenzhen Institute of Artificial Intelligence & Robotics for Society（深圳人工智能与机器人研究院）；Malong Technologies（码隆科技）
Convolutional Neural Networks (CNNs) are generally prone to noise interruptions, i.e., small image noise can cause drastic changes in the output. To suppress the noise effect to the final predication, we enhance CNNs by replacing max-pooling, strided-convolution, and average-pooling with Discrete Wavelet Transform (DWT). We present general DWT and Inverse DWT (IDWT) layers applicable to various wavelets like Haar, Daubechies, and Cohen, etc., and design wavelet integrated CNNs (WaveCNets) using these layers for image classification. In WaveCNets, feature maps are decomposed into the low-freque…
École de Technologie Supérieure, University of Québec（魁北克大学高等技术学院）；Pontifical Catholic University of Paraná（巴拉那天主教大学）
Facial expression recognition is a major problem in the domain of artificial intelligence. One of the best ways to solve this problem is the use of convolutional neural networks (CNNs). However, a large amount of data is required to train properly these networks but most of the datasets available for facial expression recognition are relatively small. A common way to circumvent the lack of data is to use CNNs trained on large datasets of different domains and fine-tuning the layers of such networks to the target domain. However, the fine-tuning process does not preserve the memory integrity as…
