The pooling operation is a cornerstone element of convolutional neural networks. These elements generate receptive fields for neurons, in which local perturbations should have minimal effect on the output activations, increasing robustness and invariance of the network. In this paper we will present an altered version of the most commonly applied method, maximum pooling, where pooling in theory is substituted by a continuous time differential equation, which generates a location sensitive pooling operation, more similar to biological receptive fields. We will present how this continuous method can be approximated numerically using discrete operations which fit ideally on a GPU. In our approach the kernel size is substituted by diffusion strength which is a continuous valued parameter, this way it can be optimized by gradient descent algorithms. We will evaluate the effect of continuous pooling on accuracy and computational need using commonly applied network architectures and datasets.
National University of Defense Technology（国防科技大学）；Chinese Academy of Sciences（中国科学院）
Practical networks for edge devices adopt shallow depth and small convolutional kernels to save memory and computational cost, which leads to a restricted receptive field. Conventional efficient learning methods focus on lightweight convolution designs, ignoring the role of the receptive field in neural network design. In this paper, we propose the Meta-Pooling framework to make the receptive field learnable for a lightweight network, which consists of parameterized pooling-based operations. Specifically, we introduce a parameterized spatial enhancer, which is composed of pooling operations to…
The size and shape of the receptive field determine how the network aggregates local information and affect the overall performance of a model considerably. Many components in a neural network, such as kernel sizes and strides for convolution and pooling operations, influence the configuration of a receptive field. However, they still rely on hyperparameters, and the receptive fields of existing models result in suboptimal shapes and sizes. Hence, we propose a simple yet effective Dynamically Optimized Pooling operation, referred to as DynOPool, which optimizes the scale factors of feature map…
There are a variety of approaches to obtain a vast receptive field with convolutional neural networks (CNNs), such as pooling or striding convolutions. Most of these approaches were initially designed for image classification and later adapted to dense prediction tasks, such as semantic segmentation. However, the major drawback of this adaptation is the loss of spatial information. Even the popular dilated convolution approach, which in theory is able to operate with full spatial resolution, needs to subsample features for large image sizes in order to make the training and inference tractable…
University of Central Florida（中佛罗里达大学）；Center for Research in Computer Vision（计算机视觉研究中心）
In this work, we explain in detail how receptive fields, effective receptive fields, and projective fields of neurons in different layers, convolution or pooling, of a Convolutional Neural Network (CNN) are calculated. While our focus here is on CNNs, the same operations, but in the reverse order, can be used to calculate these quantities for deconvolutional neural networks. These are important concepts, not only for better understanding and analyzing convolutional and deconvolutional networks, but also for optimizing their performance in real-world applications.
Harbin Institute of Technology（哈尔滨工业大学）；Changzhi University（长治学院）
In computer vision, convolutional networks (CNNs) often adopts pooling to enlarge receptive field which has the advantage of low computational complexity. However, pooling can cause information loss and thus is detrimental to further operations such as features extraction and analysis. Recently, dilated filter has been proposed to trade off between receptive field size and efficiency. But the accompanying gridding effect can cause a sparse sampling of input images with checkerboard patterns. To address this problem, in this paper, we propose a novel multi-level wavelet CNN (MWCNN) model to ach…
Inspired by the success of recent vision transformers and large kernel design in convolutional neural networks (CNNs), in this paper, we analyze and explore essential reasons for their success. We claim two factors that are critical for 3D large-scale scene understanding: a larger receptive field and operations with greater non-linearity. The former is responsible for providing long range contexts and the latter can enhance the capacity of the network. To achieve the above properties, we propose a simple yet effective long range pooling (LRP) module using dilation max pooling, which provides a…
Pooling is a critical operation in convolutional neural networks for increasing receptive fields and improving robustness to input variations. Most existing pooling operations downsample the feature maps, which is a lossy process. Moreover, they are not invertible: upsampling a downscaled feature map can not recover the lost information in the downsampling. By adopting the philosophy of the classical Lifting Scheme from signal processing, we propose LiftPool for bidirectional pooling layers, including LiftDownPool and LiftUpPool. LiftDownPool decomposes a feature map into various downsized sub…
Harbin Institute of Technology（哈尔滨工业大学）；Peking University（北京大学）
In most convolution neural networks (CNNs), downsampling hidden layers is adopted for increasing computation efficiency and the receptive field size. Such operation is commonly so-called pooling. Maximation and averaging over sliding windows (max/average pooling), and plain downsampling in the form of strided convolution are popular pooling methods. Since the pooling is a lossy procedure, a motivation of our work is to design a new pooling approach for less lossy in the dimensionality reduction. Inspired by the Fourier spectral pooling(FSP) proposed by Rippel et. al. [1], we present the Hartle…
Recent advances in deep learning have shown exciting promise in filling large holes and lead to another orientation for image inpainting. However, existing learning-based methods often create artifacts and fallacious textures because of insufficient cognition understanding. Previous generative networks are limited with single receptive type and give up pooling in consideration of detail sharpness. Human cognition is constant regardless of the target attribute. As multiple receptive fields improve the ability of abstract image characterization and pooling can keep feature invariant, specificall…
This paper reports a novel deep architecture referred to as Maxout network In Network (MIN), which can enhance model discriminability and facilitate the process of information abstraction within the receptive field. The proposed network adopts the framework of the recently developed Network In Network structure, which slides a universal approximator, multilayer perceptron (MLP) with rectifier units, to exact features. Instead of MLP, we employ maxout MLP to learn a variety of piecewise linear activation functions and to mediate the problem of vanishing gradients that can occur when using recti…
TU Darmstadt（达姆施塔特工业大学）；NEC Laboratories Europe（欧洲NEC实验室）；Oculus Research（Oculus研究院）
Most convolutional neural networks use some method for gradually downscaling the size of the hidden layers. This is commonly referred to as pooling, and is applied to reduce the number of parameters, improve invariance to certain distortions, and increase the receptive field size. Since pooling by nature is a lossy process, it is crucial that each such layer maintains the portion of the activations that is most important for the network's discriminability. Yet, simple maximization or averaging over blocks, max or average pooling, or plain downsampling in the form of strided convolutions are th…
Traditional grid/neighbor-based static pooling has become a constraint for point cloud geometry analysis. In this paper, we propose DAR-Net, a novel network architecture that focuses on dynamic feature aggregation. The central idea of DAR-Net is generating a self-adaptive pooling skeleton that considers both scene complexity and local geometry features. Providing variable semi-local receptive fields and weights, the skeleton serves as a bridge that connect local convolutional feature extractors and a global recurrent feature integrator. Experimental results on indoor scene datasets show advant…
Pooling methods are necessities for modern neural networks for increasing receptive fields and lowering down computational costs. However, commonly used hand-crafted pooling approaches, e.g., max pooling and average pooling, may not well preserve discriminative features. While many researchers have elaborately designed various pooling variants in spatial domain to handle these limitations with much progress, the temporal aspect is rarely visited where directly applying hand-crafted methods or these specialized spatial variants may not be optimal. In this paper, we derive temporal lift pooling …
In this paper, we address the task of layout-to-image translation, which aims to translate an input semantic layout to a realistic image. One open challenge widely observed in existing methods is the lack of effective semantic constraints during the image translation process, leading to models that cannot preserve the semantic information and ignore the semantic dependencies within the same object. To address this issue, we propose a novel Double Pooing GAN (DPGAN) for generating photo-realistic and semantically-consistent results from the input layout. We also propose a novel Double Pooling M…
Beijing Key Laboratory of Big Data Management and Analysis Methods（北京市大数据管理与分析方法重点实验室）；Gaoling School of Artificial Intelligence（高瓴人工智能学院）；Renmin University of China（中国人民大学）
Convolutional neural networks use regular quadrilateral convolution kernels to extract features. Since the number of parameters increases quadratically with the size of the convolution kernel, many popular models use small convolution kernels, resulting in small local receptive fields in lower layers. This paper proposes a novel log-polar space convolution (LPSC) method, where the convolution kernel is elliptical and adaptively divides its local receptive field into different regions according to the relative directions and logarithmic distances. The local receptive field grows exponentially w…
HST-MRF: Heterogeneous Swin Transformer with Multi-Receptive Field for Medical Image Segmentation
school of Mathematics and Statistics, Changsha University of Science and Technology（长沙理工大学数学与统计学院）；school of Computer and Communication Engineering, Changsha University of Science and Technology（长沙理工大学计算机与通信工程学院）
ARFC-WAHNet: Adaptive Receptive Field Convolution and Wavelet-Attentive Hierarchical Network for Infrared Small Target Detection
School of Information and Communication Engineering（信息与通信工程学院）；Laboratory of Imaging Detection and Intelligent Perception（成像检测与智能感知实验室）；University of Electronic Science and Technology of China（电子科学与技术大学）
A fundamental problem in object recognition is the development of image representations that are invariant to common transformations such as translation, rotation, and small deformations. There are multiple hypotheses regarding the source of translation invariance in CNNs. One idea is that translation invariance is due to the increasing receptive field size of neurons in successive convolution layers. Another possibility is that invariance is due to the pooling operation. We develop a simple a tool, the translation-sensitivity map, which we use to visualize and quantify the translation-invaria…
Convolutional Pose Machine is a popular neural network architecture for articulated pose estimation. In this work we explore its empirical receptive field and realize, that it can be enhanced with integration of a global context. To do so U-shaped context module is proposed and compared with the pyramid pooling and atrous spatial pyramid pooling modules, which are often used in semantic segmentation domain. The proposed neural network achieves state-of-the-art accuracy with 87.9% PCKh for single-person pose estimation on the Look Into Person dataset. A smaller version of this network runs more…
Zhejiang University（浙江大学）；Alibaba-Zhejiang University Joint Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）；Arizona State University（亚利桑那州立大学）；Deepwise AI Lab（深睿人工智能实验室）；University of Sydney（悉尼大学）
The Fast Style Transfer methods have been recently proposed to transfer a photograph to an artistic style in real-time. This task involves controlling the stroke size in the stylized results, which remains an open challenge. In this paper, we present a stroke controllable style transfer network that can achieve continuous and spatial stroke size control. By analyzing the factors that influence the stroke size, we propose to explicitly account for the receptive field and the style image scales. We propose a StrokePyramid module to endow the network with adaptive receptive fields, and two traini…
Semantic segmentation has been a hot topic across diverse research fields. Along with the success of deep convolutional neural networks, semantic segmentation has made great achievements and improvements, in terms of both urban scene parsing and indoor semantic segmentation. However, most of the state-of-the-art models are still faced with a challenge in discriminative feature learning, which limits the ability of a model to detect multi-scale objects and to guarantee semantic consistency inside one object or distinguish different adjacent objects with similar appearance. In this paper, a prac…
University of Kansas（堪萨斯大学）；Wetland Studies and Solutions, Inc.（湿地研究与解决方案公司）
Mean field approximation methodology has laid the foundation of modern Continuous Random Field (CRF) based solutions for the refinement of semantic segmentation. In this paper, we propose to relax the hard constraint of mean field approximation - minimizing the energy term of each node from probabilistic graphical model, by a global optimization with the proposed dilated sparse convolution module (DSConv). In addition, adaptive global average-pooling and adaptive global max-pooling are implemented as replacements of fully connected layers. In order to integrate DSConv, we design an end-to-end,…
Imperial College London（帝国理工学院）；Fudan University（复旦大学）
Dilated convolutions are widely used in deep semantic segmentation models as they can enlarge the filters' receptive field without adding additional weights nor sacrificing spatial resolution. However, as dilated convolutional filters do not possess positional knowledge about the pixels on semantically meaningful contours, they could lead to ambiguous predictions on object boundaries. In addition, although dilating the filter can expand its receptive field, the total number of sampled pixels remains unchanged, which usually comprises a small fraction of the receptive field's total area. Inspir…
With the success of deep learning in classifying short trimmed videos, more attention has been focused on temporally segmenting and classifying activities in long untrimmed videos. State-of-the-art approaches for action segmentation utilize several layers of temporal convolution and temporal pooling. Despite the capabilities of these approaches in capturing temporal dependencies, their predictions suffer from over-segmentation errors. In this paper, we propose a multi-stage architecture for the temporal action segmentation task that overcomes the limitations of the previous approaches. The fir…
Expanding the receptive field to capture large-scale context is key to obtaining good performance in dense prediction tasks, such as human pose estimation. While many state-of-the-art fully-convolutional architectures enlarge the receptive field by reducing resolution using strided convolution or pooling layers, the most straightforward strategy is adopting large filters. This, however, is costly because of the quadratic increase in the number of parameters and multiply-add operations. In this work, we explore using learnable box filters to allow for convolution with arbitrarily large kernel s…
Montreal Institute for Learning Algorithms（蒙特利尔学习算法研究所）；Computer Vision Center, Barcelona（巴塞罗那计算机视觉中心）；Facebook AI Research（Facebook人工智能研究）
State-of-the-art semantic segmentation approaches increase the receptive field of their models by using either a downsampling path composed of poolings/strided convolutions or successive dilated convolutions. However, it is not clear which operation leads to best results. In this paper, we systematically study the differences introduced by distinct receptive field enlargement methods and their impact on the performance of a novel architecture, called Fully Convolutional DenseResNet (FC-DRN). FC-DRN has a densely connected backbone composed of residual networks. Following standard image segment…
StripRFNet: A Strip Receptive Field and Shape-Aware Network for Road Damage Detection
Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院数字地球科学重点实验室）；International Research Center of Big Data for Sustainable Development Goals（可持续发展大数据国际研究中心）；University of Chinese Academy of Sciences（中国科学院大学）；Southeast University（东南大学）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）
P2AT: Pyramid Pooling Axial Transformer for Real-time Semantic Segmentation
School of Computer Science, Zhejiang Normal University（浙江师范大学计算机科学学院）；School of Mathematical Medicine, Zhejiang Normal University（浙江师范大学数学医学院）；Zhejiang Institute of Photoelectronics & Zhejiang Institute for Advanced Light Source, Zhejiang Normal University（浙江师范大学光电研究所与浙江先进光源研究所）；School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications（重庆邮电大学通信与信息工程学院）
Facebook（脸书）；Google（谷歌）；The University of Hong Kong（香港大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Carnegie Mellon University（卡内基梅隆大学）
State-of-the-art results of semantic segmentation are established by Fully Convolutional neural Networks (FCNs). FCNs rely on cascaded convolutional and pooling layers to gradually enlarge the receptive fields of neurons, resulting in an indirect way of modeling the distant contextual dependence. In this work, we advocate the use of spatially recurrent layers (i.e. ReNet layers) which directly capture global contexts and lead to improved feature representations. We demonstrate the effectiveness of ReNet layers by building a Naive deep ReNet (N-ReNet), which achieves competitive performance on …
We propose a novel method for temporally pooling frames in a video for the task of human action recognition. The method is motivated by the observation that there are only a small number of frames which, together, contain sufficient information to discriminate an action class present in a video, from the rest. The proposed method learns to pool such discriminative and informative frames, while discarding a majority of the non-informative frames in a single temporal scan of the video. Our algorithm does so by continuously predicting the discriminative importance of each video frame and subseque…
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…
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…
University of Wollongong（卧龙岗大学）；China University of Geosciences（中国地质大学）
This paper proposes three simple, compact yet effective representations of depth sequences, referred to respectively as Dynamic Depth Images (DDI), Dynamic Depth Normal Images (DDNI) and Dynamic Depth Motion Normal Images (DDMNI), for both isolated and continuous action recognition. These dynamic images are constructed from a segmented sequence of depth maps using hierarchical bidirectional rank pooling to effectively capture the spatial-temporal information. Specifically, DDI exploits the dynamics of postures over time and DDNI and DDMNI exploit the 3D structural information captured by depth…
University of Maryland, College Park, MD USA（马里兰大学帕克分校）；Nanjing University, Nanjing, China（南京大学）
Global information is essential for dense prediction problems, whose goal is to compute a discrete or continuous label for each pixel in the images. Traditional convolutional layers in neural networks, initially designed for image classification, are restrictive in these problems since the filter size limits their receptive fields. In this work, we propose to replace any traditional convolutional layer with an autoregressive moving-average (ARMA) layer, a novel module with an adjustable receptive field controlled by the learnable autoregressive coefficients. Compared with traditional convoluti…
Scene text removal aims to remove the text and fill the regions with perceptually plausible background information in natural images. It has attracted increasing attention due to its various applications in privacy protection, scene text retrieval, and text editing. With the development of deep learning, the previous methods have achieved significant improvements. However, most of the existing methods seem to ignore the large perceptive fields and global information. The pioneer method can get significant improvements by only changing training data from the cropped image to the full image. In …
BEVANet: Bilateral Efficient Visual Attention Network for Real-Time Semantic Segmentation
Graduate Institute of Networking and Multimedia, National Taiwan University（网络与多媒体研究所，国立台湾大学）；Department of Computer Science and Information Engineering, National Taiwan University（计算机科学与信息工程系，国立台湾大学）
Automated medical image segmentation plays a key role in quantitative research and diagnostics. Convolutional neural networks based on the U-Net architecture are the state-of-the-art. A key disadvantage is the hard-coding of the receptive field size, which requires architecture optimization for each segmentation task. Furthermore, increasing the receptive field results in an increasing number of weights. Recently, Neural Ordinary Differential Equations (NODE) have been proposed, a new type of continuous depth deep neural network. This framework allows for a dynamic receptive field at a fixed m…
Continuous Sign Language Recognition (CSLR) is a challenging research task due to the lack of accurate annotation on the temporal sequence of sign language data. The recent popular usage is a hybrid model based on "CNN + RNN" for CSLR. However, when extracting temporal features in these works, most of the methods using a fixed temporal receptive field and cannot extract the temporal features well for each sign language word. In order to obtain more accurate temporal features, this paper proposes a multi-scale temporal network (MSTNet). The network mainly consists of three parts. The Resnet and…
National Institutes of Health Clinical Center（美国国立卫生研究院临床中心）
Accurately predicting and detecting interstitial lung disease (ILD) patterns given any computed tomography (CT) slice without any pre-processing prerequisites, such as manually delineated regions of interest (ROIs), is a clinically desirable, yet challenging goal. The majority of existing work relies on manually-provided ILD ROIs to extract sampled 2D image patches from CT slices and, from there, performs patch-based ILD categorization. Acquiring manual ROIs is labor intensive and serves as a bottleneck towards fully-automated CT imaging ILD screening over large-scale populations. Furthermore,…
In this work, we address the face parsing task with a Fully-Convolutional continuous CRF Neural Network (FC-CNN) architecture. In contrast to previous face parsing methods that apply region-based subnetwork hundreds of times, our FC-CNN is fully convolutional with high segmentation accuracy. To achieve this goal, FC-CNN integrates three subnetworks, a unary network, a pairwise network and a continuous Conditional Random Field (C-CRF) network into a unified framework. The high-level semantic information and low-level details across different convolutional layers are captured by the convolutiona…
University of Pennsylvania（宾夕法尼亚大学）；Dartmouth College（达特茅斯学院）
The state-of-the-art in semantic segmentation is currently represented by fully convolutional networks (FCNs). However, FCNs use large receptive fields and many pooling layers, both of which cause blurring and low spatial resolution in the deep layers. As a result FCNs tend to produce segmentations that are poorly localized around object boundaries. Prior work has attempted to address this issue in post-processing steps, for example using a color-based CRF on top of the FCN predictions. However, these approaches require additional parameters and low-level features that are difficult to tune an…
City University of Hong Kong（香港城市大学）；University of Cambridge（剑桥大学）
Image segmentation is a fundamental task in image analysis and clinical practice. The current state-of-the-art techniques are based on U-shape type encoder-decoder networks with skip connections, called U-Net. Despite the powerful performance reported by existing U-Net type networks, they suffer from several major limitations. Issues include the hard coding of the receptive field size, compromising the performance and computational cost, as well as the fact that they do not account for inherent noise in the data. They have problems associated with discrete layers, and do not offer any theoreti…
Existing image fusion methods pay few research attention to image fusion efficiency and network architecture. However, the efficiency and accuracy of image fusion has an important impact in practical applications. To solve this problem, we propose an \textit{efficient autonomous evolution image fusion method, dubed by AE-Netv2}. Different from other image fusion methods based on deep learning, AE-Netv2 is inspired by human brain cognitive mechanism. Firstly, we discuss the influence of different network architecture on image fusion quality and fusion efficiency, which provides a reference for …
First steps towards a mathematical theory of deep convolutional neural networks for feature extraction were made---for the continuous-time case---in Mallat, 2012, and Wiatowski and Bölcskei, 2015. This paper considers the discrete case, introduces new convolutional neural network architectures, and proposes a mathematical framework for their analysis. Specifically, we establish deformation and translation sensitivity results of local and global nature, and we investigate how certain structural properties of the input signal are reflected in the corresponding feature vectors. Our theory applies…
