Capsule networks are a type of neural network that have recently gained increased popularity. They consist of groups of neurons, called capsules, which encode properties of objects or object parts. The connections between capsules encrypt part-whole relationships between objects through routing algorithms which route the output of capsules from lower level layers to upper level layers. Capsule networks can reach state-of-the-art results on many challenging computer vision tasks, such as MNIST, Fashion-MNIST, and Small-NORB. However, most capsule network implementations use two to three capsule layers, which limits their applicability as expressivity grows exponentially with depth. One approach to overcome such limitations would be to train deeper network architectures, as it has been done for convolutional neural networks with much increased success. In this paper, we propose a methodology to train deeper capsule networks using residual connections, which is evaluated on four datasets and three different routing algorithms. Our experimental results show that in fact, performance increases when training deeper capsule networks. The source code is available on https://github.com/moejoe95/res-capsnet.
National Institute of Technology Karnataka（卡纳塔克邦国家理工学院）
The capsule network is a distinct and promising segment of the neural network family that drew attention due to its unique ability to maintain the equivariance property by preserving the spatial relationship amongst the features. The capsule network has attained unprecedented success over image classification tasks with datasets such as MNIST and affNIST by encoding the characteristic features into the capsules and building the parse-tree structure. However, on the datasets involving complex foreground and background regions such as CIFAR-10, the performance of the capsule network is sub-optim…
University of Innsbruck（因斯布鲁克大学）；DeepOpinion（DeepOpinion公司）
Capsule networks are a class of neural networks that achieved promising results on many computer vision tasks. However, baseline capsule networks have failed to reach state-of-the-art results on more complex datasets due to the high computation and memory requirements. We tackle this problem by proposing a new network architecture, called Momentum Capsule Network (MoCapsNet). MoCapsNets are inspired by Momentum ResNets, a type of network that applies reversible residual building blocks. Reversible networks allow for recalculating activations of the forward pass in the backpropagation algorithm…
In capsule networks, the routing algorithm connects capsules in consecutive layers, enabling the upper-level capsules to learn higher-level concepts by combining the concepts of the lower-level capsules. Capsule networks are known to have a few advantages over conventional neural networks, including robustness to 3D viewpoint changes and generalization capability. However, some studies have reported negative experimental results. Nevertheless, the reason for this phenomenon has not been analyzed yet. We empirically analyzed the effect of five different routing algorithms. The experimental resu…
We present group equivariant capsule networks, a framework to introduce guaranteed equivariance and invariance properties to the capsule network idea. Our work can be divided into two contributions. First, we present a generic routing by agreement algorithm defined on elements of a group and prove that equivariance of output pose vectors, as well as invariance of output activations, hold under certain conditions. Second, we connect the resulting equivariant capsule networks with work from the field of group convolutional networks. Through this connection, we provide intuitions of how both meth…
In this study, we investigate in-shop clothing retrieval performance of densely-connected Capsule Networks with dynamic routing. To achieve this, we propose Triplet-based design of Capsule Network architecture with two different feature extraction methods. In our design, Stacked-convolutional (SC) and Residual-connected (RC) blocks are used to form the input of capsule layers. Experimental results show that both of our designs outperform all variants of the baseline study, namely FashionNet, without relying on the landmark information. Moreover, when compared to the SOTA architectures on cloth…
Center for Research in Computer Vision（计算机视觉研究中心）；University of Central Florida（中佛罗里达大学）
The recent advances in Deep Convolutional Neural Networks (DCNNs) have shown extremely good results for video human action classification, however, action detection is still a challenging problem. The current action detection approaches follow a complex pipeline which involves multiple tasks such as tube proposals, optical flow, and tube classification. In this work, we present a more elegant solution for action detection based on the recently developed capsule network. We propose a 3D capsule network for videos, called VideoCapsuleNet: a unified network for action detection which can jointly …
Norwegian University of Science and Technology（挪威科技大学）；Innlandet Hospital Trust（内陆医院信托）；University of Oslo（奥斯陆大学）
We propose a novel pathology-sensitive deep learning model (PS-DeVCEM) for frame-level anomaly detection and multi-label classification of different colon diseases in video capsule endoscopy (VCE) data. Our proposed model is capable of coping with the key challenge of colon apparent heterogeneity caused by several types of diseases. Our model is driven by attention-based deep multiple instance learning and is trained end-to-end on weakly labeled data using video labels instead of detailed frame-by-frame annotation. The spatial and temporal features are obtained through ResNet50 and residual Lo…
TalkingData；Inception Institute of Artificial Intelligence（Inception人工智能研究院）
Capsule networks (CapsNets) are capable of modeling visual hierarchical relationships, which is achieved by the "routing-by-agreement" mechanism. This paper proposes a pairwise agreement mechanism to build capsules, inspired by the feature interactions of factorization machines (FMs). The proposed method has a much lower computation complexity. We further proposed a new CapsNet architecture that combines the strengths of residual networks in representing low-level visual features and CapsNets in modeling the relationships of parts to wholes. We conduct comprehensive experiments to compare the …
Tsinghua University（清华大学）；Polish Academy of Sciences（波兰科学院）；Shanghai Qi Zhi Institute（上海期智研究院）
Capsule networks, which incorporate the paradigms of connectionism and symbolism, have brought fresh insights into artificial intelligence. The capsule, as the building block of capsule networks, is a group of neurons represented by a vector to encode different features of an entity. The information is extracted hierarchically through capsule layers via routing algorithms. Here, we introduce a quantum capsule network (dubbed QCapsNet) together with an efficient quantum dynamic routing algorithm. To benchmark the performance of the QCapsNet, we carry out extensive numerical simulations on the c…
We present and evaluate a new deep neural network architecture for automatic thoracic disease detection on chest X-rays. Deep neural networks have shown great success in a plethora of visual recognition tasks such as image classification and object detection by stacking multiple layers of convolutional neural networks (CNN) in a feed-forward manner. However, the performance gain by going deeper has reached bottlenecks as a result of the trade-off between model complexity and discrimination power. We address this problem by utilizing the recently developed routing-by agreement mechanism in our …
Very deep convolutional networks have been central to the largest advances in image recognition performance in recent years. One example is the Inception architecture that has been shown to achieve very good performance at relatively low computational cost. Recently, the introduction of residual connections in conjunction with a more traditional architecture has yielded state-of-the-art performance in the 2015 ILSVRC challenge; its performance was similar to the latest generation Inception-v3 network. This raises the question of whether there are any benefit in combining the Inception architec…
Automatic image colourisation is the computer vision research path that studies how to colourise greyscale images (for restoration). Deep learning techniques improved image colourisation yielding astonishing results. These differ by various factors, such as structural differences, input types, user assistance, etc. Most of them, base the architectural structure on convolutional layers with no emphasis on layers specialised in object features extraction. We introduce a novel downsampling upsampling architecture named TUCaN (Tiny UCapsNet) that exploits the collaboration of convolutional layers …
Residual networks are the current state of the art on ImageNet. Similar work in the direction of utilizing shortcut connections has been done extremely recently with derivatives of residual networks and with highway networks. This work potentially challenges our understanding that CNNs learn layers of local features that are followed by increasingly global features. Through qualitative visualization and empirical analysis, we explore the purpose that residual skip connections serve. Our assessments show that the residual shortcut connections force layers to refine features, as expected. We als…
Filter level pruning is an effective method to accelerate the inference speed of deep CNN models. Although numerous pruning algorithms have been proposed, there are still two open issues. The first problem is how to prune residual connections. We propose to prune both channels inside and outside the residual connections via a KL-divergence based criterion. The second issue is pruning with limited data. We observe an interesting phenomenon: directly pruning on a small dataset is usually worse than fine-tuning a small model which is pruned or trained from scratch on the large dataset. Knowledge …
Jagiellonian University（雅盖隆大学）；MILA（蒙特利尔学习算法研究所）；Université de Montréal（蒙特利尔大学）；Facebook（脸书）；Aalto University（阿尔托大学）；University of Bonn（波恩大学）
Residual networks (Resnets) have become a prominent architecture in deep learning. However, a comprehensive understanding of Resnets is still a topic of ongoing research. A recent view argues that Resnets perform iterative refinement of features. We attempt to further expose properties of this aspect. To this end, we study Resnets both analytically and empirically. We formalize the notion of iterative refinement in Resnets by showing that residual connections naturally encourage features of residual blocks to move along the negative gradient of loss as we go from one block to the next. In addi…
Training-Time Optical Priors for Wireless Capsule Endoscopy Classification: Hemoglobin-Aware Input Fusion with Cross-Vendor Evaluation
Department of Biomedical Engineering, University of Texas Southwestern Medical Center（生物医学工程系，德克萨斯西南医学中心）；Department of Internal Medicine, University of Texas Southwestern Medical Center（内科系，德克萨斯西南医学中心）；Department of Radiation Oncology, Stanford University（放射肿瘤学系，斯坦福大学）；VELVETECH, LLC（VELVETECH公司）；Division of Digestive and Liver Diseases, Clements University Hospital（消化和肝病系，克莱门斯大学医院）；Internal Medicine, Division of Digestive and Liver Diseases, Parkland Hospital（内科，消化和肝病系，帕克兰医院）
Convolutional neural network (CNN) depth is of crucial importance for image super-resolution (SR). However, we observe that deeper networks for image SR are more difficult to train. The low-resolution inputs and features contain abundant low-frequency information, which is treated equally across channels, hence hindering the representational ability of CNNs. To solve these problems, we propose the very deep residual channel attention networks (RCAN). Specifically, we propose a residual in residual (RIR) structure to form very deep network, which consists of several residual groups with long sk…
DFKI - German Research Center for Artificial Intelligence（德国人工智能研究中心）；Birla Institute of Technology and Science (BITS) Pilani（皮拉尼伯拉理工学院（BITS皮拉尼））；University of Applied Sciences Mannheim（曼海姆应用科学大学）；University of Kaiserslautern - TUK（凯泽斯劳滕大学（TUK））
Dense pixel matching is required for many computer vision algorithms such as disparity, optical flow or scene flow estimation. Feature Pyramid Networks (FPN) have proven to be a suitable feature extractor for CNN-based dense matching tasks. FPN generates well localized and semantically strong features at multiple scales. However, the generic FPN is not utilizing its full potential, due to its reasonable but limited localization accuracy. Thus, we present ResFPN -- a multi-resolution feature pyramid network with multiple residual skip connections, where at any scale, we leverage the information…
Knowledge distillation (KD) is generally considered as a technique for performing model compression and learned-label smoothing. However, in this paper, we study and investigate the KD approach from a new perspective: we study its efficacy in training a deeper network without any residual connections. We find that in most of the cases, non-residual student networks perform equally or better than their residual versions trained on raw data without KD (baseline network). Surprisingly, in some cases, they surpass the accuracy of baseline networks even with the inferior teachers. After a certain d…
Graz University of Technology（格拉茨技术大学）；York University（约克大学）
Two-stream Convolutional Networks (ConvNets) have shown strong performance for human action recognition in videos. Recently, Residual Networks (ResNets) have arisen as a new technique to train extremely deep architectures. In this paper, we introduce spatiotemporal ResNets as a combination of these two approaches. Our novel architecture generalizes ResNets for the spatiotemporal domain by introducing residual connections in two ways. First, we inject residual connections between the appearance and motion pathways of a two-stream architecture to allow spatiotemporal interaction between the two …
Augmenting neural networks with skip connections, as introduced in the so-called ResNet architecture, surprised the community by enabling the training of networks of more than 1,000 layers with significant performance gains. This paper deciphers ResNet by analyzing the effect of skip connections, and puts forward new theoretical results on the advantages of identity skip connections in neural networks. We prove that the skip connections in the residual blocks facilitate preserving the norm of the gradient, and lead to stable back-propagation, which is desirable from optimization perspective. W…
School of Computer and Information Technology, Shanxi University（山西大学计算机与信息技术学院）；Harbin Institute of Technology（哈尔滨工业大学）
Recent years have witnessed great success of convolutional neural network (CNN) for various problems both in low and high level visions. Especially noteworthy is the residual network which was originally proposed to handle high-level vision problems and enjoys several merits. This paper aims to extend the merits of residual network, such as skip connection induced fast training, for a typical low-level vision problem, i.e., single image super-resolution. In general, the two main challenges of existing deep CNN for supper-resolution lie in the gradient exploding/vanishing problem and large numb…
In this work, we propose ReStoCNet, a residual stochastic multilayer convolutional Spiking Neural Network (SNN) composed of binary kernels, to reduce the synaptic memory footprint and enhance the computational efficiency of SNNs for complex pattern recognition tasks. ReStoCNet consists of an input layer followed by stacked convolutional layers for hierarchical input feature extraction, pooling layers for dimensionality reduction, and fully-connected layer for inference. In addition, we introduce residual connections between the stacked convolutional layers to improve the hierarchical feature l…
National Institute of Allergy and Infectious Diseases（美国国家过敏和传染病研究所）
Segmentation and quantification of white matter hyperintensities (WMHs) are of great importance in studying and understanding various neurological and geriatric disorders. Although automatic methods have been proposed for WMH segmentation on magnetic resonance imaging (MRI), manual corrections are often necessary to achieve clinically practical results. Major challenges for WMH segmentation stem from their inhomogeneous MRI intensities, random location and size distributions, and MRI noise. The presence of other brain anatomies or diseases with enhanced intensities adds further difficulties. T…
SynA-ResNet: Spike-driven ResNet Achieved through OR Residual Connection
School of Software, Liaoning Technical University（辽宁工程技术大学软件学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of California, Santa Cruz（加州大学圣克鲁兹分校）；University of Electronic Science and Technology of China（电子科技大学）
Tohoku University（东北大学）；RIKEN Center for AIP（理化学研究所AIP中心）
In this paper, we study design of deep neural networks for tasks of image restoration. We propose a novel style of residual connections dubbed "dual residual connection", which exploits the potential of paired operations, e.g., up- and down-sampling or convolution with large- and small-size kernels. We design a modular block implementing this connection style; it is equipped with two containers to which arbitrary paired operations are inserted. Adopting the "unraveled" view of the residual networks proposed by Veit et al., we point out that a stack of the proposed modular blocks allows the fir…
Madan Mohan Malaviya University of Technology（马丹·莫汉·马拉维亚技术大学）；Malaviya National Institute of Technology Jaipur（斋浦尔马拉维亚国家理工学院）
In this paper we propose a novel 3D CNN network with localized residual connections for hyperspectral image classification. Our work chalks a comparative study with the existing methods employed for abstracting deeper features and propose a model which incorporates residual features from multiple stages in the network. The proposed architecture processes individual spatiospectral feature rich cubes from hyperspectral images through 3D convolutional layers. The residual connections result in improved performance due to assimilation of both low-level and high-level features. We conduct experimen…
Indian Institute of Information Technology, Sri City（斯里城印度信息技术学院）；Indian Institute of Information Technology, Allahabad（阿拉哈巴德印度信息技术学院）；National Cheng Kung University（国立成功大学）
Residual networks (ResNets) have been utilized for various computer vision and image processing applications. The residual connection improves the training of the network with better gradient flow. A residual block consists of few convolutional layers having trainable parameters, which leads to overfitting. Moreover, the present residual networks are not able to utilize the high and low frequency information suitably, which also challenges the generalization capability of the network. In this paper, a frequency disentangled residual network (FDResNet) is proposed to tackle these issues. Specif…
Tencent Youtu Lab（腾讯优图实验室）；University of California, Santa Cruz（加州大学圣克鲁兹分校）
Although residual connection enables training very deep neural networks, it is not friendly for online inference due to its multi-branch topology. This encourages many researchers to work on designing DNNs without residual connections at inference. For example, RepVGG re-parameterizes multi-branch topology to a VGG-like (single-branch) model when deploying, showing great performance when the network is relatively shallow. However, RepVGG can not transform ResNet to VGG equivalently because re-parameterizing methods can only be applied to linear blocks and the non-linear layers (ReLU) have to b…
Residual networks (ResNets) employ skip connections in their networks -- reusing activations from previous layers -- to improve training convergence, but these skip connections create challenges for hardware implementations of ResNets. The hardware must either wait for skip connections to be processed before processing more incoming data or buffer them elsewhere. Without skip connections, ResNets would be more hardware-efficient. Thus, we present the teacher-student learning method to gradually prune away all of a ResNet's skip connections, constructing a network we call NonResNet. We show tha…
Spiking Neural Networks (SNNs) may offer an energy-efficient alternative for implementing deep learning applications. In recent years, there have been several proposals focused on supervised (conversion, spike-based gradient descent) and unsupervised (spike timing dependent plasticity) training methods to improve the accuracy of SNNs on large-scale tasks. However, each of these methods suffer from scalability, latency and accuracy limitations. In this paper, we propose novel algorithmic techniques of modifying the SNN configuration with backward residual connections, stochastic softmax and hyb…
Residual Neural Networks (ResNets) achieve state-of-the-art performance in many computer vision problems. Compared to plain networks without residual connections (PlnNets), ResNets train faster, generalize better, and suffer less from the so-called degradation problem. We introduce simplified (but still nonlinear) versions of ResNets and PlnNets for which these discrepancies still hold, although to a lesser degree. We establish a 1-1 mapping between simplified ResNets and simplified PlnNets, and show that they are exactly equivalent to each other in expressive power for the same computational …
Université Paris-Est（巴黎东部大学）；École des Ponts ParisTech（巴黎高科桥路学校）
Deep neural networks with skip-connections, such as ResNet, show excellent performance in various image classification benchmarks. It is though observed that the initial motivation behind them - training deeper networks - does not actually hold true, and the benefits come from increased capacity, rather than from depth. Motivated by this, and inspired from ResNet, we propose a simple Dirac weight parameterization, which allows us to train very deep plain networks without explicit skip-connections, and achieve nearly the same performance. This parameterization has a minor computational cost at …
Tsinghua University（清华大学）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Shenzhen University（深圳大学）；Peng Cheng Laboratory（鹏城实验室）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Tencent（腾讯）
North China Electric Power University（华北电力大学）；University of Missouri（密苏里大学）
A residual-networks family with hundreds or even thousands of layers dominates major image recognition tasks, but building a network by simply stacking residual blocks inevitably limits its optimization ability. This paper proposes a novel residual-network architecture, Residual networks of Residual networks (RoR), to dig the optimization ability of residual networks. RoR substitutes optimizing residual mapping of residual mapping for optimizing original residual mapping. In particular, RoR adds level-wise shortcut connections upon original residual networks to promote the learning capability …
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Colorado Boulder（科罗拉多大学博尔德分校）
Photorealistic style transfer is an image editing task with the goal to modify an image to match the style of another image while ensuring the result looks like a real photograph. A limitation of existing models is that they have many parameters, which in turn prevents their use for larger image resolutions and leads to slower run-times. We introduce two mechanisms that enable our design of a more compact model that we call PhotoWCT$^2$, which preserves state-of-art stylization strength and photorealism. First, we introduce blockwise training to perform coarse-to-fine feature transformations t…
Air Force Engineering University（空军工程大学）；Laval University（拉瓦尔大学）；Xidian University（西安电子科技大学）
Human activity recognition (HAR) has become a popular topic in research because of its wide application. With the development of deep learning, new ideas have appeared to address HAR problems. Here, a deep network architecture using residual bidirectional long short-term memory (LSTM) cells is proposed. The advantages of the new network include that a bidirectional connection can concatenate the positive time direction (forward state) and the negative time direction (backward state). Second, residual connections between stacked cells act as highways for gradients, which can pass underlying inf…
Development of Skip Connection in Deep Neural Networks for Computer Vision and Medical Image Analysis: A Survey
School of Computer Science and Engineering, Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology（计算机科学与工程学院、智能机器人湖北省重点实验室、武汉理工大学）；School of Computer Science, Wuhan University（计算机科学学院、武汉大学）
Sapienza University（罗马第一大学）；University of Udine（乌迪内大学）
Improving existing neural network architectures can involve several design choices such as manipulating the loss functions, employing a diverse learning strategy, exploiting gradient evolution at training time, optimizing the network hyper-parameters, or increasing the architecture depth. The latter approach is a straightforward solution, since it directly enhances the representation capabilities of a network; however, the increased depth generally incurs in the well-known vanishing gradient problem. In this paper, borrowing from different methods addressing this issue, we introduce an interla…
This paper presents results of applying Inception v4 deep convolutional neural network to ICIAR-2018 Breast Cancer Classification Grand Challenge, part a. The Challenge task is to classify breast cancer biopsy results, presented in form of hematoxylin and eosin stained images. Breast cancer classification is of primary interest to the medical practitioners and thus binary classification of breast cancer images have been under investigation by many researchers, but multi-class categorization of histology breast images have been challenging due to the subtle differences among the categories. In …
Deep learning methods have shown outstanding performance in many applications, including single-image super-resolution (SISR). With residual connection architecture, deeply stacked convolutional neural networks provide a substantial performance boost for SISR, but their huge parameters and computational loads are impractical for real-world applications. Thus, designing lightweight models with acceptable performance is one of the major tasks in current SISR research. The objective of lightweight network design is to balance a computational load and reconstruction performance. Most of the previo…
Deep convolutional neural networks have been demonstrated to be effective for SISR in recent years. On the one hand, residual connections and dense connections have been used widely to ease forward information and backward gradient flows to boost performance. However, current methods use residual connections and dense connections separately in most network layers in a sub-optimal way. On the other hand, although various networks and methods have been designed to improve computation efficiency, save parameters, or utilize training data of multiple scale factors for each other to boost performan…
