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 the standard. In this paper, we aim to leverage recent results on image downscaling for the purposes of deep learning. Inspired by the human visual system, which focuses on local spatial changes, we propose detail-preserving pooling (DPP), an adaptive pooling method that magnifies spatial changes and preserves important structural detail. Importantly, its parameters can be learned jointly with the rest of the network. We analyze some of its theoretical properties and show its empirical benefits on several datasets and networks, where DPP consistently outperforms previous pooling approaches.
In the framework of convolutional neural networks that lie at the heart of deep learning, downsampling is often performed with a max-pooling operation that only retains the element with maximum activation, while completely discarding the information contained in other elements in a pooling region. To address this issue, a novel pooling scheme, Ordinal Pooling Network (OPN), is introduced in this work. OPN rearranges all the elements of a pooling region in a sequence and assigns different weights to these elements based upon their orders in the sequence, where the weights are learned via the gr…
Shahrood University of Technology（沙赫鲁德工业大学）；Faculty of Electrical & Robotics Engineering（电气与机器人工程学院）
Nowadays, Deep Neural Networks are among the main tools used in various sciences. Convolutional Neural Network is a special type of DNN consisting of several convolution layers, each followed by an activation function and a pooling layer. The pooling layer is an important layer that executes the down-sampling on the feature maps coming from the previous layer and produces new feature maps with a condensed resolution. This layer drastically reduces the spatial dimension of input. It serves two main purposes. The first is to reduce the number of parameters or weights, thus lessening the computat…
Aalto University（阿尔托大学）；Federal Institute of Ceará（塞阿拉联邦研究所）；University of Manchester（曼彻斯特大学）
Graph pooling is a central component of a myriad of graph neural network (GNN) architectures. As an inheritance from traditional CNNs, most approaches formulate graph pooling as a cluster assignment problem, extending the idea of local patches in regular grids to graphs. Despite the wide adherence to this design choice, no work has rigorously evaluated its influence on the success of GNNs. In this paper, we build upon representative GNNs and introduce variants that challenge the need for locality-preserving representations, either using randomization or clustering on the complement graph. Stri…
Faculty of Mathematics and Computer Science Jagiellonian University（雅盖隆大学数学与计算机科学学院）；Ardigen
Global pooling, such as max- or sum-pooling, is one of the key ingredients in deep neural networks used for processing images, texts, graphs and other types of structured data. Based on the recent DeepSets architecture proposed by Zaheer et al. (NIPS 2017), we introduce a Set Aggregation Network (SAN) as an alternative global pooling layer. In contrast to typical pooling operators, SAN allows to embed a given set of features to a vector representation of arbitrary size. We show that by adjusting the size of embedding, SAN is capable of preserving the whole information from the input. In experi…
National Institute of Technology Trichy（特里奇国家理工学院）；Indian Institute of Technology Palakkad（帕拉卡德印度理工学院）
With the introduction of anti-aliased convolutional neural networks (CNN), there has been some resurgence in relooking the way pooling is done in CNNs. The fundamental building block of the anti-aliased CNN has been the application of Gaussian smoothing before the pooling operation to reduce the distortion due to aliasing thereby making CNNs shift invariant. Wavelet based approaches have also been proposed as a possibility of additional noise removal capability and gave interesting results for even segmentation tasks. However, all the approaches proposed completely remove the high frequency co…
Spatial downsampling layers are favored in convolutional neural networks (CNNs) to downscale feature maps for larger receptive fields and less memory consumption. However, for discriminative tasks, there is a possibility that these layers lose the discriminative details due to improper pooling strategies, which could hinder the learning process and eventually result in suboptimal models. In this paper, we present a unified framework over the existing downsampling layers (e.g., average pooling, max pooling, and strided convolution) from a local importance view. In this framework, we analyze the…
Global Average Pooling (GAP) is used by default on the channel-wise attention mechanism to extract channel descriptors. However, the simple global aggregation method of GAP is easy to make the channel descriptors have homogeneity, which weakens the detail distinction between feature maps, thus affecting the performance of the attention mechanism. In this work, we propose a novel method for channel-wise attention network, called Stochastic Region Pooling (SRP), which makes the channel descriptors more representative and diversity by encouraging the feature map to have more or wider important fe…
Information Technology University（信息技术大学）；The Home Depot（家得宝）
Body-Mass-Index (BMI) conveys important information about one's life such as health and socio-economic conditions. Large-scale automatic estimation of BMIs can help predict several societal behaviors such as health, job opportunities, friendships, and popularity. The recent works have either employed hand-crafted geometrical face features or face-level deep convolutional neural network features for face to BMI prediction. The hand-crafted geometrical face feature lack generalizability and face-level deep features don't have detailed local information. Although useful, these methods missed the …
PVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection
College of Computer Science and Technology, Taiyuan University of Technology（太原理工大学计算机科学与技术学院）；Key Laboratory of Machine Perception, Peking University（北京大学机器感知实验室）；University of Pisa（比萨大学）；University of Trento（特伦托大学）
A Synergistic CNN-Transformer Network with Pooling Attention Fusion for Hyperspectral Image Classification
College of Engineering（工程学院）；School of Electronic Information and Communications（电子信息与通信学院）；Changchun Institute of Optics, Fine Mechanics and Physics（长春光学精密机械与物理研究所）；School of Computer Science and Technology（计算机科学与技术学院）；School of Intelligent Manufacturing and Electrical Engineering（智能制造与电气工程学院）
Existing point cloud feature learning networks often incorporate sequences of sampling, neighborhood grouping, neighborhood-wise feature learning, and feature aggregation to learn high-semantic point features that represent the global context of a point cloud. Unfortunately, the compounded loss of information concerning granularity and non-maximum point features due to sampling and max pooling could adversely affect the high-semantic point features from existing networks such that they are insufficient to represent the local context of a point cloud, which in turn may hinder the network in dis…
ETH Zurich（苏黎世联邦理工学院）；Adobe Research（奥多比研究院）；IIT Bombay（印度理工学院孟买分校）
We propose a novel learnable representation for detail-preserving shape deformation. The goal of our method is to warp a source shape to match the general structure of a target shape, while preserving the surface details of the source. Our method extends a traditional cage-based deformation technique, where the source shape is enclosed by a coarse control mesh termed \emph{cage}, and translations prescribed on the cage vertices are interpolated to any point on the source mesh via special weight functions. The use of this sparse cage scaffolding enables preserving surface details regardless of …
King Fahd University of Petroleum and Minerals（法赫德国王石油与矿业大学）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）
In spite of the improvements achieved by the several denoising algorithms over the years, many of them still fail at preserving the fine details of the image after denoising. This is as a result of the smooth-out effect they have on the images. Most neural network-based algorithms have achieved better quantitative performance than the classical denoising algorithms. However, they also suffer from qualitative (visual) performance as a result of the smooth-out effect. In this paper, we propose an algorithm to address this shortcoming. We propose a deep collaborative filtering-based (Deep-CoFiB) …
East China Normal University（华东师范大学）；Videt Tech（Videt科技）
The accuracy of OCR is usually affected by the quality of the input document image and different kinds of marred document images hamper the OCR results. Among these scenarios, the low-resolution image is a common and challenging case. In this paper, we propose the cascaded networks for document image super-resolution. Our model is composed by the Detail-Preserving Networks with small magnification. The loss function with perceptual terms is designed to simultaneously preserve the original patterns and enhance the edge of the characters. These networks are trained with the same architecture and…
We consider the task of semi-supervised video object segmentation (VOS). Our approach mitigates shortcomings in previous VOS work by addressing detail preservation and temporal consistency using visual warping. In contrast to prior work that uses full optical flow, we introduce a new foreground-targeted visual warping approach that learns flow fields from VOS data. We train a flow module to capture detailed motion between frames using two weakly-supervised losses. Our object-focused approach of warping previous foreground object masks to their positions in the target frame enables detailed mas…
Tencent（腾讯）；Jilin University（吉林大学）；NLPR Institute of Automation CAS（中国科学院自动化研究所模式识别国家重点实验室）；School of Artificial Intelligence UCAS（中国科学院大学人工智能学院）；CASIA-LLVision Joint Lab（中国科学院自动化研究所-联影智能联合实验室）
Weakly supervised object localization(WSOL) remains an open problem given the deficiency of finding object extent information using a classification network. Although prior works struggled to localize objects through various spatial regularization strategies, we argue that how to extract object structural information from the trained classification network is neglected. In this paper, we propose a two-stage approach, termed structure-preserving activation (SPA), toward fully leveraging the structure information incorporated in convolutional features for WSOL. First, a restricted activation mod…
Korea Advanced Institute of Science and Technology（韩国科学技术院）
Single-image 3D human reconstruction aims to reconstruct the 3D textured surface of the human body given a single image. While implicit function-based methods recently achieved reasonable reconstruction performance, they still bear limitations showing degraded quality in both surface geometry and texture from an unobserved view. In response, to generate a realistic textured surface, we propose ReFu, a coarse-to-fine approach that refines the projected backside view image and fuses the refined image to predict the final human body. To suppress the diffused occupancy that causes noise in project…
Currently, reliable and accurate ship detection in optical remote sensing images is still challenging. Even the state-of-the-art convolutional neural network (CNN) based methods cannot obtain very satisfactory results. To more accurately locate the ships in diverse orientations, some recent methods conduct the detection via the rotated bounding box. However, it further increases the difficulty of detection, because an additional variable of ship orientation must be accurately predicted in the algorithm. In this paper, a novel CNN-based ship detection method is proposed, by overcoming some comm…
Since convolutional neural networks perform well in learning generalizable image priors from large-scale data, these models have been widely used in image denoising tasks. However, the computational complexity increases dramatically as well on complex model. In this paper, We propose a novel lightweight Complementary Attention Module, which includes a density module and a sparse module, which can cooperatively mine dense and sparse features for feature complementary learning to build an efficient lightweight architecture. Moreover, to reduce the loss of details caused by denoising, this paper …
Mustapha Stambouli University of Mascara（马斯卡拉穆斯塔法·斯坦布利大学）；University of Orleans（奥尔良大学）；Université Paris Saclay（巴黎萨克雷大学）；Univ Evry（埃夫里大学）
This paper investigates the usage of kernel functions at the different layers in a convolutional neural network. We carry out extensive studies of their impact on convolutional, pooling and fully-connected layers. We notice that the linear kernel may not be sufficiently effective to fit the input data distributions, whereas high order kernels prone to over-fitting. This leads to conclude that a trade-off between complexity and performance should be reached. We show how one can effectively leverage kernel functions, by introducing a more distortion aware pooling layers which reduces over-fittin…
Indian Institute of Technology Madras (IITM)（印度理工学院马德拉斯分校）；Healthcare Technology Innovation Centre (HTIC), IITM（印度理工学院马德拉斯分校医疗技术创新中心）
Several variants of Convolutional Neural Networks (CNN) have been developed for Magnetic Resonance (MR) image reconstruction. Among them, U-Net has shown to be the baseline architecture for MR image reconstruction. However, sub-sampling is performed by its pooling layers, causing information loss which in turn leads to blur and missing fine details in the reconstructed image. We propose a modification to the U-Net architecture to recover fine structures. The proposed network is a wavelet packet transform based encoder-decoder CNN with residual learning called CNN. The proposed WCNN has discret…
In this paper, we propose a multi-level texture encoding and representation network (MuLTER) for texture-related applications. Based on a multi-level pooling architecture, the MuLTER network simultaneously leverages low- and high-level features to maintain both texture details and spatial information. Such a pooling architecture involves few extra parameters and keeps feature dimensions fixed despite of the changes of image sizes. In comparison with state-of-the-art texture descriptors, the MuLTER network yields higher recognition accuracy on typical texture datasets such as MINC-2500 and GTOS…
Virginia Tech（弗吉尼亚理工大学）；Kuwait University（科威特大学）；Adobe Research（Adobe 研究院）；University of Maryland College Park（马里兰大学帕克分校）
We present an algorithm for re-rendering a person from a single image under arbitrary poses. Existing methods often have difficulties in hallucinating occluded contents photo-realistically while preserving the identity and fine details in the source image. We first learn to inpaint the correspondence field between the body surface texture and the source image with a human body symmetry prior. The inpainted correspondence field allows us to transfer/warp local features extracted from the source to the target view even under large pose changes. Directly mapping the warped local features to an RG…
Feature pyramids and iterative refinement have recently led to great progress in optical flow estimation. However, downsampling in feature pyramids can cause blending of foreground objects with the background, which will mislead subsequent decisions in the iterative processing. The results are missing details especially in the flow of thin and of small structures. We propose a novel Residual Feature Pyramid Module (RFPM) which retains important details in the feature map without changing the overall iterative refinement design of the optical flow estimation. RFPM incorporates a residual struct…
Xi'an University of Architecture and Technology（西安建筑科技大学）
Retinal vessels are important biomarkers for many ophthalmological and cardiovascular diseases. Hence, it is of great significance to develop automatic models for computer-aided diagnosis. Existing methods, such as U-Net follow the encoder-decoder pipeline, where detailed information is lost in the encoder in order to achieve a large field of view. Although spatial detailed information could be recovered partly in the decoder, while there is noise in the high-resolution feature maps of the encoder. And, we argue this encoder-decoder architecture is inefficient for vessel segmentation. In this …
Subgroup performance analysis of adaptation strategies for chest X-ray foundation models
Imperial College London（帝国理工学院）；Royal Brompton Hospital（皇家布朗普顿医院）；Causality in Healthcare AI Hub（医疗保健AI因果关系中心）；National Heart & Lung Institute（国家心肺研究所）
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…
UT Austin（德克萨斯大学奥斯汀分校）；Adobe Research（奥多比研究院）；IIT Bombay（印度理工学院孟买分校）
This paper introduces a data-driven shape completion approach that focuses on completing geometric details of missing regions of 3D shapes. We observe that existing generative methods lack the training data and representation capacity to synthesize plausible, fine-grained details with complex geometry and topology. Our key insight is to copy and deform patches from the partial input to complete missing regions. This enables us to preserve the style of local geometric features, even if it drastically differs from the training data. Our fully automatic approach proceeds in two stages. First, we …
Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院智能信息技术北京市重点实验室）；Computer Vision Laboratory, ETH Zurich（苏黎世联邦理工学院计算机视觉实验室）
Recently, numerous algorithms have been developed to tackle the problem of light field super-resolution (LFSR), i.e., super-resolving low-resolution light fields to gain high-resolution views. Despite delivering encouraging results, these approaches are all convolution-based, and are naturally weak in global relation modeling of sub-aperture images necessarily to characterize the inherent structure of light fields. In this paper, we put forth a novel formulation built upon Transformers, by treating LFSR as a sequence-to-sequence reconstruction task. In particular, our model regards sub-apertur…
Change detection (CD) is an essential earth observation technique. It captures the dynamic information of land objects. With the rise of deep learning, convolutional neural networks (CNN) have shown great potential in CD. However, current CNN models introduce backbone architectures that lose detailed information during learning. Moreover, current CNN models are heavy in parameters, which prevents their deployment on edge devices such as UAVs. In this work, we tackle this issue by proposing RDP-Net: a region detail preserving network for CD. We propose an efficient training strategy that constr…
Beihang University（北京航空航天大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；National University of Singapore（新加坡国立大学）；Sea AI Lab（Sea人工智能实验室）
In this paper, we address the makeup transfer and removal tasks simultaneously, which aim to transfer the makeup from a reference image to a source image and remove the makeup from the with-makeup image respectively. Existing methods have achieved much advancement in constrained scenarios, but it is still very challenging for them to transfer makeup between images with large pose and expression differences, or handle makeup details like blush on cheeks or highlight on the nose. In addition, they are hardly able to control the degree of makeup during transferring or to transfer a specified part…
Chalmers University of Technology（查尔姆斯理工大学）；Czech Technical University in Prague（布拉格捷克技术大学）
Visual localization is the problem of estimating the camera pose of a given image with respect to a known scene. Visual localization algorithms are a fundamental building block in advanced computer vision applications, including Mixed and Virtual Reality systems. Many algorithms used in practice represent the scene through a Structure-from-Motion (SfM) point cloud and use 2D-3D matches between a query image and the 3D points for camera pose estimation. As recently shown, image details can be accurately recovered from SfM point clouds by translating renderings of the sparse point clouds to imag…
AID-DTI: Accelerating High-fidelity Diffusion Tensor Imaging with Detail-Preserving Model-based Deep Learning
Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院保罗·C·劳特伯生物医学成像研究中心）；University of Chinese Academy of Sciences（中国科学院大学）；State Key Laboratory of Software Development Environment, Beihang University（北京航空航天大学软件开发环境国家重点实验室）；Institute of International Innovation, Beihang University（北京航空航天大学国际创新研究院）；Peng Cheng Laboratory（鹏城实验室）
Lightweight Data-Free Denoising for Detail-Preserving Biomedical Image Restoration
School of Computation, Information and Technology, Technical University of Munich（计算信息学院，慕尼黑技术大学）；Helmholtz AI, Helmholtz Munich - German Research Center for Environmental Health（海德堡人工智能，海德堡-德国环境健康研究所以及研究中心）；School of Biomedical Engineering and Imaging Sciences, King’s College London（生物医学工程与成像科学学院，伦敦国王学院）
