As a variant of standard convolution, a dilated convolution can control effective receptive fields and handle large scale variance of objects without introducing additional computational costs. To fully explore the potential of dilated convolution, we proposed a new type of dilated convolution (referred to as inception convolution), where the convolution operations have independent dilation patterns among different axes, channels and layers. To develop a practical method for learning complex inception convolution based on the data, a simple but effective search algorithm, referred to as efficient dilation optimization (EDO), is developed. Based on statistical optimization, the EDO method operates in a low-cost manner and is extremely fast when it is applied on large scale datasets. Empirical results validate that our method achieves consistent performance gains for image recognition, object detection, instance segmentation, human detection, and human pose estimation. For instance, by simply replacing the 3x3 standard convolution in the ResNet-50 backbone with inception convolution, we significantly improve the AP of Faster R-CNN from 36.4% to 39.2% on MS COCO.
Bernstein Center for Computational Neuroscience（伯恩斯坦计算神经科学中心）；Université Paris-Est（巴黎东部大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
In this paper we propose a CNN architecture for semantic image segmentation. We introduce a new 'bilateral inception' module that can be inserted in existing CNN architectures and performs bilateral filtering, at multiple feature-scales, between superpixels in an image. The feature spaces for bilateral filtering and other parameters of the module are learned end-to-end using standard backpropagation techniques. The bilateral inception module addresses two issues that arise with general CNN segmentation architectures. First, this module propagates information between (super) pixels while respec…
University of Kansas（堪萨斯大学）；Ainstein Inc.（Ainstein公司）
Object detection in challenging situations such as scale variation, occlusion, and truncation depends not only on feature details but also on contextual information. Most previous networks emphasize too much on detailed feature extraction through deeper and wider networks, which may enhance the accuracy of object detection to certain extent. However, the feature details are easily being changed or washed out after passing through complicated filtering structures. To better handle these challenges, the paper proposes a novel framework, multi-scale, deep inception convolutional neural network (M…
Peking University（北京大学）；Harvard Medical School（哈佛医学院）；Beijing Institute of Big Data Research（北京大数据研究院）
Extracting multi-scale information is key to semantic segmentation. However, the classic convolutional neural networks (CNNs) encounter difficulties in achieving multi-scale information extraction: expanding convolutional kernel incurs the high computational cost and using maximum pooling sacrifices image information. The recently developed dilated convolution solves these problems, but with the limitation that the dilation rates are fixed and therefore the receptive field cannot fit for all objects with different sizes in the image. We propose an adaptivescale convolutional neural network (AS…
The inception network has been shown to provide good performance on image classification problems, but there are not much evidences that it is also effective for the image restoration or pixel-wise labeling problems. For image restoration problems, the pooling is generally not used because the decimated features are not helpful for the reconstruction of an image as the output. Moreover, most deep learning architectures for the restoration problems do not use dense prediction that need lots of training parameters. From these observations, for enjoying the performance of inception-like structure…
In the last few years, Deep Learning (DL) has been showing superior performance in different modalities of biomedical image analysis. Several DL architectures have been proposed for classification, segmentation, and detection tasks in medical imaging and computational pathology. In this paper, we propose a new DL architecture, the NABLA-N network, with better feature fusion techniques in decoding units for dermoscopic image segmentation tasks. The NABLA-N network has several advances for segmentation tasks. First, this model ensures better feature representation for semantic segmentation with …
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Shenzhen Technology University（深圳技术大学）
Semantic segmentation usually benefits from global contexts, fine localisation information, multi-scale features, etc. To advance Transformer-based segmenters with these aspects, we present a simple yet powerful semantic segmentation architecture, termed as IncepFormer. IncepFormer has two critical contributions as following. First, it introduces a novel pyramid structured Transformer encoder which harvests global context and fine localisation features simultaneously. These features are concatenated and fed into a convolution layer for final per-pixel prediction. Second, IncepFormer integrates…
Since convolutional neural network(CNN)models emerged,several tasks in computer vision have actively deployed CNN models for feature extraction. However,the conventional CNN models have a high computational cost and require high memory capacity, which is impractical and unaffordable for commercial applications such as real-time on-road object detection on embedded boards or mobile platforms. To tackle this limitation of CNN models, this paper proposes a wide-residual-inception (WR-Inception) network, which constructs the architecture based on a residual inception unit that captures objects of …
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；University of Mannheim（曼海姆大学）
Contextual information is crucial for semantic segmentation. However, finding the optimal trade-off between keeping desired fine details and at the same time providing sufficiently large receptive fields is non trivial. This is even more so, when objects or classes present in an image significantly vary in size. Dilated convolutions have proven valuable for semantic segmentation, because they allow to increase the size of the receptive field without sacrificing image resolution. However, in current state-of-the-art methods, dilation parameters are hand-tuned and fixed. In this paper, we presen…
Beijing National Research Center for Information Science and Technology (BNRist)（北京信息科学与技术国家研究中心）；Tsinghua University（清华大学）；MEGVII Technology（旷视科技）；Aberystwyth University（阿伯里斯特威斯大学）
We propose a universal building block of Convolutional Neural Network (ConvNet) to improve the performance without any inference-time costs. The block is named Diverse Branch Block (DBB), which enhances the representational capacity of a single convolution by combining diverse branches of different scales and complexities to enrich the feature space, including sequences of convolutions, multi-scale convolutions, and average pooling. After training, a DBB can be equivalently converted into a single conv layer for deployment. Unlike the advancements of novel ConvNet architectures, DBB complicate…
University of Electronic Science and Technology of China（电子科技大学）
Dermoscopy image detection stays a tough task due to the weak distinguishable property of the object.Although the deep convolution neural network signifigantly boosted the performance on prevelance computer vision tasks in recent years,there remains a room to explore more robust and precise models to the problem of low contrast image segmentation.Towards the challenge of Lesion Segmentation in ISBI 2017,we built a symmetrical identity inception fully convolution network which is based on only 10 reversible inception blocks,every block composed of four convolution branches with combination of d…
Thanks to recent advances in CNNs, solid improvements have been made in semantic segmentation of high resolution remote sensing imagery. However, most of the previous works have not fully taken into account the specific difficulties that exist in remote sensing tasks. One of such difficulties is that objects are small and crowded in remote sensing imagery. To tackle with this challenging task we have proposed a novel architecture called local feature extraction (LFE) module attached on top of dilated front-end module. The LFE module is based on our findings that aggressively increasing dilatio…
Pohang University of Science and Technology（浦项科技大学）
Semantic segmentation networks adopt transfer learning from image classification networks which occurs a shortage of spatial context information. For this reason, we propose Spatial Context Memoization (SpaM), a bypassing branch for spatial context by retaining the input dimension and constantly communicating its spatial context and rich semantic information mutually with the backbone network. Multi-scale context information for semantic segmentation is crucial for dealing with diverse sizes and shapes of target objects in the given scene. Conventional multi-scale context scheme adopts multipl…
Megvii Inc（旷视科技）；University of Chinese Academy of Sciences (UCAS)（中国科学院大学）；Center for Research on Intelligent Perception and Computing (CRIPAC)（智能感知与计算研究中心）；National Laboratory of Pattern Recognition (NLPR)（模式识别国家重点实验室）；Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）
Most existing human pose estimation (HPE) methods exploit multi-scale information by fusing feature maps of four different spatial sizes, \ie $1/4$, $1/8$, $1/16$, and $1/32$ of the input image. There are two drawbacks of this strategy: 1) feature maps of different spatial sizes may be not well aligned spatially, which potentially hurts the accuracy of keypoint location; 2) these scales are fixed and inflexible, which may restrict the generalization ability over various human sizes. Towards these issues, we propose an adaptive dilated convolution (ADC). It can generate and fuse multi-scale fea…
We present an interpretation of Inception modules in convolutional neural networks as being an intermediate step in-between regular convolution and the depthwise separable convolution operation (a depthwise convolution followed by a pointwise convolution). In this light, a depthwise separable convolution can be understood as an Inception module with a maximally large number of towers. This observation leads us to propose a novel deep convolutional neural network architecture inspired by Inception, where Inception modules have been replaced with depthwise separable convolutions. We show that th…
This paper presents a novel 3D object detection framework that processes LiDAR data directly on its native representation: range images. Benefiting from the compactness of range images, 2D convolutions can efficiently process dense LiDAR data of a scene. To overcome scale sensitivity in this perspective view, a novel range-conditioned dilation (RCD) layer is proposed to dynamically adjust a continuous dilation rate as a function of the measured range. Furthermore, localized soft range gating combined with a 3D box-refinement stage improves robustness in occluded areas, and produces overall mor…
Deep convolutional neural networks (DCNNs) are an influential tool for solving various problems in the machine learning and computer vision fields. In this paper, we introduce a new deep learning model called an Inception- Recurrent Convolutional Neural Network (IRCNN), which utilizes the power of an inception network combined with recurrent layers in DCNN architecture. We have empirically evaluated the recognition performance of the proposed IRCNN model using different benchmark datasets such as MNIST, CIFAR-10, CIFAR- 100, and SVHN. Experimental results show similar or higher recognition acc…
Combining Self-attention and Dilation Convolutional for Semantic Segmentation of Coal Maceral Groups
School of Electronic and Electrical Engineering, Shanghai University of Engineering Science（上海工程技术大学电子电气工程学院）；China Electronics Technology Group Corporation No.15 Research Institute（中国电子科技集团第十五研究所）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Department of Manufacture Management of Angang Steel Co.,Ltd.（鞍钢钢铁有限公司制造管理部）
Machine learning and computer vision have driven many of the greatest advances in the modeling of Deep Convolutional Neural Networks (DCNNs). Nowadays, most of the research has been focused on improving recognition accuracy with better DCNN models and learning approaches. The recurrent convolutional approach is not applied very much, other than in a few DCNN architectures. On the other hand, Inception-v4 and Residual networks have promptly become popular among computer the vision community. In this paper, we introduce a new DCNN model called the Inception Recurrent Residual Convolutional Neura…
Traditional works have shown that patches in a natural image tend to redundantly recur many times inside the image, both within the same scale, as well as across different scales. Make full use of these multi-scale information can improve the image restoration performance. However, the current proposed deep learning based restoration methods do not take the multi-scale information into account. In this paper, we propose a dilated convolution based inception module to learn multi-scale information and design a deep network for single image super-resolution. Different dilated convolution learns …
Shantou University（汕头大学）；Sapienza University of Rome（罗马大学）；Pusan National University（釜山国立大学）
Inspired by the development of deep learning in computer vision and object detection, the proposed algorithm considers an encoder-decoder architecture with hierarchical feature learning and dilated convolution, named U-Hierarchical Dilated Network (U-HDN), to perform crack detection in an end-to-end method. Crack characteristics with multiple context information are automatically able to learn and perform end-to-end crack detection. Then, a multi-dilation module embedded in an encoder-decoder architecture is proposed. The crack features of multiple context sizes can be integrated into the mult…
Harbin Institute of Technology（哈尔滨工业大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）；City University of Hong Kong（香港城市大学）；Shenzhen Research Institute, City University of Hong Kong（香港城市大学深圳研究院）
Crowd counting is critical for numerous video surveillance scenarios. One of the main issues in this task is how to handle the dramatic scale variations of pedestrians caused by the perspective effect. To address this issue, this paper proposes a novel convolution neural network-based crowd counting method, termed Perspective-guided Fractional-Dilation Network (PFDNet). By modeling the continuous scale variations, the proposed PFDNet is able to select the proper fractional dilation kernels for adapting to different spatial locations. It significantly improves the flexibility of the state-of-th…
Capturing feature information effectively is of great importance in vision tasks. With the development of convolutional neural networks (CNNs), concepts like residual connection and multiple scales promote continual performance gains on diverse deep learning vision tasks. However, the existing methods do not organically combined advantages of these valid ideas. In this paper, we propose a novel CNN architecture called GoogLe2Net, it consists of residual feature-reutilization inceptions (ResFRI) or split residual feature-reutilization inceptions (Split-ResFRI) which create transverse passages b…
Recently, with the advent of deep convolutional neural networks (DCNN), the improvements in visual saliency prediction research are impressive. One possible direction to approach the next improvement is to fully characterize the multi-scale saliency-influential factors with a computationally-friendly module in DCNN architectures. In this work, we proposed an end-to-end dilated inception network (DINet) for visual saliency prediction. It captures multi-scale contextual features effectively with very limited extra parameters. Instead of utilizing parallel standard convolutions with different ker…
Low dose computed tomography is a mainstream for clinical applications. How-ever, compared to normal dose CT, in the low dose CT (LDCT) images, there are stronger noise and more artifacts which are obstacles for practical applications. In the last few years, convolution-based end-to-end deep learning methods have been widely used for LDCT image denoising. Recently, transformer has shown superior performance over convolution with more feature interactions. Yet its ap-plications in LDCT denoising have not been fully cultivated. Here, we propose a convolution-free T2T vision transformer-based Enc…
Symmetry-Aware 9D Pose Estimation with Sim(3)-Consistent Feature and Spherical Inception Convolution
National Engineering Research Center for Robot Visual Perception and Control, School of Robotics and Artificial Intelligence, Hunan University（机器人视觉感知与控制国家工程研究中心，机器人与人工智能学院，湖南大学）；Beijing Spacecrafts, China Academy of Space Technology（北京航天器，中国航天科技研究院）；School of Computing and Information Systems, The University of Melbourne（计算与信息学院，墨尔本大学）
Colorectal cancer (CRC) is one of the most commonly diagnosed cancers and a leading cause of cancer deaths in the United States. Colorectal polyps that grow on the intima of the colon or rectum is an important precursor for CRC. Currently, the most common way for colorectal polyp detection and precancerous pathology is the colonoscopy. Therefore, accurate colorectal polyp segmentation during the colonoscopy procedure has great clinical significance in CRC early detection and prevention. In this paper, we propose a novel end-to-end deep learning framework for the colorectal polyp segmentation. …
Politehnica University of Timişoara（蒂米什瓦拉理工大学）；West University of Timişoara（蒂米什瓦拉西部大学）；The eAustria Research Institute（eAustria研究所）
Edges are a basic and fundamental feature in image processing, that are used directly or indirectly in huge amount of applications. Inspired by the expansion of image resolution and processing power dilated convolution techniques appeared. Dilated convolution have impressive results in machine learning, we discuss here the idea of dilating the standard filters which are used in edge detection algorithms. In this work we try to put together all our previous and current results by using instead of the classical convolution filters a dilated one. We compare the results of the edge detection algor…
Korea Advanced Institute of Science and Technology（韩国高等科学技术院）
Recent advances in deep learning have shown promising results in many low-level vision tasks. However, solving the single-image-based view synthesis is still an open problem. In particular, the generation of new images at parallel camera views given a single input image is of great interest, as it enables 3D visualization of the 2D input scenery. We propose a novel network architecture to perform stereoscopic view synthesis at arbitrary camera positions along the X-axis, or Deep 3D Pan, with "t-shaped" adaptive kernels equipped with globally and locally adaptive dilations. Our proposed network…
IMSE: Efficient U-Net-based Speech Enhancement using Inception Depthwise Convolution and Amplitude-Aware Linear Attention
College of Electronics and Information Engineering, Shenzhen University（深圳大学电子与信息工程学院）；Shenzhen, China Information Center, Shenzhen University（深圳大学深圳信息中心）
In this work, we propose Dilated Point Convolutions (DPC). In a thorough ablation study, we show that the receptive field size is directly related to the performance of 3D point cloud processing tasks, including semantic segmentation and object classification. Point convolutions are widely used to efficiently process 3D data representations such as point clouds or graphs. However, we observe that the receptive field size of recent point convolutional networks is inherently limited. Our dilated point convolutions alleviate this issue, they significantly increase the receptive field size of poin…
Télécom Paris（巴黎电信学院）；Institut Polytechnique de Paris（巴黎综合理工学院）；Université Paris-Dauphine（巴黎多芬大学）；PSL Research University（巴黎文理研究大学）；University of São Paulo（圣保罗大学）；Sorbonne Université（索邦大学）；CNRS（法国国家科学研究中心）；LIP6（LIP6实验室）
Spatial relations between objects in an image have proved useful for structural object recognition. Structural constraints can act as regularization in neural network training, improving generalization capability with small datasets. Several relations can be modeled as a morphological dilation of a reference object with a structuring element representing the semantics of the relation, from which the degree of satisfaction of the relation between another object and the reference object can be derived. However, dilation is not differentiable, requiring an approximation to be used in the context …
Rowan University（罗文大学）；University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）
Magnetic resonance imaging (MRI) is routinely used for brain tumor diagnosis, treatment planning, and post-treatment surveillance. Recently, various models based on deep neural networks have been proposed for the pixel-level segmentation of tumors in brain MRIs. However, the structural variations, spatial dissimilarities, and intensity inhomogeneity in MRIs make segmentation a challenging task. We propose a new end-to-end brain tumor segmentation architecture based on U-Net that integrates Inception modules and dilated convolutions into its contracting and expanding paths. This allows us to ex…
University of Sydney（悉尼大学）；Huawei Technologies（华为技术有限公司）；Peking University（北京大学）
With the tremendous advances in the architecture and scale of convolutional neural networks (CNNs) over the past few decades, they can easily reach or even exceed the performance of humans in certain tasks. However, a recently discovered shortcoming of CNNs is that they are vulnerable to adversarial attacks. Although the adversarial robustness of CNNs can be improved by adversarial training, there is a trade-off between standard accuracy and adversarial robustness. From the neural architecture perspective, this paper aims to improve the adversarial robustness of the backbone CNNs that have a s…
There are many award-winning pre-trained Convolutional Neural Network (CNN), which have a common phenomenon of increasing depth in convolutional layers. However, I inspect on VGG network, which is one of the famous model submitted to ILSVRC-2014, to show that slight modification in the basic architecture can enhance the accuracy result of the image classification task. In this paper, We present two improve architectures of pre-trained VGG-16 and VGG-19 networks that apply transfer learning when trained on a different dataset. I report a series of experimental result on various modification of …
