Vision transformers have been successfully applied to image recognition tasks due to their ability to capture long-range dependencies within an image. However, there are still gaps in both performance and computational cost between transformers and existing convolutional neural networks (CNNs). In this paper, we aim to address this issue and develop a network that can outperform not only the canonical transformers, but also the high-performance convolutional models. We propose a new transformer based hybrid network by taking advantage of transformers to capture long-range dependencies, and of CNNs to model local features. Furthermore, we scale it to obtain a family of models, called CMTs, obtaining much better accuracy and efficiency than previous convolution and transformer based models. In particular, our CMT-S achieves 83.5% top-1 accuracy on ImageNet, while being 14x and 2x smaller on FLOPs than the existing DeiT and EfficientNet, respectively. The proposed CMT-S also generalizes well on CIFAR10 (99.2%), CIFAR100 (91.7%), Flowers (98.7%), and other challenging vision datasets such as COCO (44.3% mAP), with considerably less computational cost.
School of Electronic and Information, Wuhan University（武汉大学电子信息学院）
We propose a simple yet effective model for Single Image Super-Resolution (SISR), by combining the merits of Residual Learning and Convolutional Sparse Coding (RL-CSC). Our model is inspired by the Learned Iterative Shrinkage-Threshold Algorithm (LISTA). We extend LISTA to its convolutional version and build the main part of our model by strictly following the convolutional form, which improves the network's interpretability. Specifically, the convolutional sparse codings of input feature maps are learned in a recursive manner, and high-frequency information can be recovered from these CSCs. M…
Hunter College, CUNY（纽约市立大学亨特学院）；The Graduate Center, CUNY（纽约市立大学研究生中心）
Transfer learning is widely used in computer vision (CV), natural language processing (NLP) and achieves great success. Most transfer learning systems are based on the same modality (e.g. RGB image in CV and text in NLP). However, the cross-modality transfer learning (CMTL) systems are scarce. In this work, we study CMTL from 2D to 3D sensor to explore the upper bound performance of 3D sensor only systems, which play critical roles in robotic navigation and perform well in low light scenarios. While most CMTL pipelines from 2D to 3D vision are complicated and based on Convolutional Neural Netw…
Idiap Research Institute（伊迪亚普研究所）；École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）；University of Rome La Sapienza（罗马第一大学）
Since Convolutional Neural Networks (CNNs) have become the leading learning paradigm in visual recognition, Naive Bayes Nearest Neighbour (NBNN)-based classifiers have lost momentum in the community. This is because (1) such algorithms cannot use CNN activations as input features; (2) they cannot be used as final layer of CNN architectures for end-to-end training , and (3) they are generally not scalable and hence cannot handle big data. This paper proposes a framework that addresses all these issues, thus bringing back NBNNs on the map. We solve the first by extracting CNN activations from lo…
For vehicle autonomy, driver assistance and situational awareness, it is necessary to operate at day and night, and in all weather conditions. In particular, long wave infrared (LWIR) sensors that receive predominantly emitted radiation have the capability to operate at night as well as during the day. In this work, we employ a polarised LWIR (POL-LWIR) camera to acquire data from a mobile vehicle, to compare and contrast four different convolutional neural network (CNN) configurations to detect other vehicles in video sequences. We evaluate two distinct and promising approaches, two-stage det…
Rotation-Robust Regression with Convolutional Model Trees
Department of Automation, Harbin Institute of Technology, Shenzhen, China（自动化系，哈尔滨工业大学，深圳）；Department of Computing Science, University of Alberta, Edmonton, Canada（计算机科学系，阿尔伯塔大学，爱德蒙顿）
City University of Hong Kong（香港城市大学）；Singapore Telecommunications Limited（新加坡电信有限公司）；Nanyang Technological University（南洋理工大学）
Various architectures (such as GoogLeNets, ResNets, and DenseNets) have been proposed. However, the existing networks usually suffer from either redundancy of convolutional layers or insufficient utilization of parameters. To handle these challenging issues, we propose Micro-Dense Nets, a novel architecture with global residual learning and local micro-dense aggregations. Specifically, residual learning aims to efficiently retrieve features from different convolutional blocks, while the micro-dense aggregation is able to enhance each block and avoid redundancy of convolutional layers by lessen…
Deep Convolutional Neural Networks Meet Variational Shape Compactness Priors for Image Segmentation
Hong Kong Baptist University（香港浸会大学）；Hong Kong Center for Cerebro-Cardiovascular Health Engineering（香港脑心健康工程中心）；Zhejiang Normal University（浙江师范大学）；Norwegian Research Center（挪威研究中心）
Real-time Video Target Tracking Algorithm Utilizing Convolutional Neural Networks (CNN)
Northeastern University（东北大学）；University of California San Diego（加州大学圣地亚哥分校）；Georgia Institute of Technology（佐治亚理工学院）；Northern Arizona University（北亚利桑那大学）
Student engagement is an important factor in meeting the goals of virtual learning programs. Automatic measurement of student engagement provides helpful information for instructors to meet learning program objectives and individualize program delivery. Many existing approaches solve video-based engagement measurement using the traditional frameworks of binary classification (classifying video snippets into engaged or disengaged classes), multi-class classification (classifying video snippets into multiple classes corresponding to different levels of engagement), or regression (estimating a co…
University of Surrey（萨里大学）；Queen Mary University of London（伦敦玛丽女王大学）；Chinese Academy of Sciences（中国科学院）
Deep learning, in particular Convolutional Neural Network (CNN), has achieved promising results in face recognition recently. However, it remains an open question: why CNNs work well and how to design a 'good' architecture. The existing works tend to focus on reporting CNN architectures that work well for face recognition rather than investigate the reason. In this work, we conduct an extensive evaluation of CNN-based face recognition systems (CNN-FRS) on a common ground to make our work easily reproducible. Specifically, we use public database LFW (Labeled Faces in the Wild) to train CNNs, un…
South China University of Technology（华南理工大学）；University of Southampton（南安普顿大学）；City University of Hong Kong（香港城市大学）
Despite the tremendous success in computer vision, deep convolutional networks suffer from serious computation costs and redundancies. Although previous works address this issue by enhancing diversities of filters, they have not considered the complementarity and the completeness of the internal structure of the convolutional network. To deal with these problems, a novel Inner-Imaging architecture is proposed in this paper, which allows relationships between channels to meet the above requirement. Specifically, we organize the channel signal points in groups using convolutional kernels to mode…
University of Pennsylvania（宾夕法尼亚大学）；Ryerson University（瑞尔森大学）
This paper addresses the challenge of 3D full-body human pose estimation from a monocular image sequence. Here, two cases are considered: (i) the image locations of the human joints are provided and (ii) the image locations of joints are unknown. In the former case, a novel approach is introduced that integrates a sparsity-driven 3D geometric prior and temporal smoothness. In the latter case, the former case is extended by treating the image locations of the joints as latent variables. A deep fully convolutional network is trained to predict the uncertainty maps of the 2D joint locations. The …
Chinese Academy of Sciences（中国科学院）；National University of Singapore（新加坡国立大学）；Sun Yat-sen University（中山大学）；Adobe Research（Adobe研究院）；China-Singapore Institute of Digital Media（中新数字媒体研究院）
Both parametric and non-parametric approaches have demonstrated encouraging performances in the human parsing task, namely segmenting a human image into several semantic regions (e.g., hat, bag, left arm, face). In this work, we aim to develop a new solution with the advantages of both methodologies, namely supervision from annotated data and the flexibility to use newly annotated (possibly uncommon) images, and present a quasi-parametric human parsing model. Under the classic K Nearest Neighbor (KNN)-based nonparametric framework, the parametric Matching Convolutional Neural Network (M-CNN) i…
Nagoya University（名古屋大学）；Aichi Cancer Center（爱知县癌症中心）；National Institute of Informatics（国立信息学研究所）
Recent advances in deep learning, like 3D fully convolutional networks (FCNs), have improved the state-of-the-art in dense semantic segmentation of medical images. However, most network architectures require severely downsampling or cropping the images to meet the memory limitations of today's GPU cards while still considering enough context in the images for accurate segmentation. In this work, we propose a novel approach that utilizes auto-context to perform semantic segmentation at higher resolutions in a multi-scale pyramid of stacked 3D FCNs. We train and validate our models on a dataset …
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Facebook Inc.（脸书公司）；Texas A&M University（得克萨斯农工大学）
Conventionally, image denoising and high-level vision tasks are handled separately in computer vision. In this paper, we cope with the two jointly and explore the mutual influence between them. First we propose a convolutional neural network for image denoising which achieves the state-of-the-art performance. Second we propose a deep neural network solution that cascades two modules for image denoising and various high-level tasks, respectively, and use the joint loss for updating only the denoising network via back-propagation. We demonstrate that on one hand, the proposed denoiser has the ge…
The Hong Kong Polytechnic University（香港理工大学）；Bavarian Forest National Park（巴伐利亚森林国家公园）；Albert-Ludwigs-Universität Freiburg（弗赖堡大学）
The stability and ability of an ecosystem to withstand climate change is directly linked to its biodiversity. Dead trees are a key indicator of overall forest health, housing one-third of forest ecosystem biodiversity, and constitute 8%of the global carbon stocks. They are decomposed by several natural factors, e.g. climate, insects and fungi. Accurate detection and modeling of dead wood mass is paramount to understanding forest ecology, the carbon cycle and decomposers. We present a novel method to construct precise shape contours of dead trees from aerial photographs by combining established…
Beijing University of Posts and Telecommunications（北京邮电大学）
PCANet, as one noticeable shallow network, employs the histogram representation for feature pooling. However, there are three main problems about this kind of pooling method. First, the histogram-based pooling method binarizes the feature maps and leads to inevitable discriminative information loss. Second, it is difficult to effectively combine other visual cues into a compact representation, because the simple concatenation of various visual cues leads to feature representation inefficiency. Third, the dimensionality of histogram-based output grows exponentially with the number of feature ma…
In the recent years, public use of artistic effects for editing and beautifying images has encouraged researchers to look for new approaches to this task. Most of the existing methods apply artistic effects to the whole image. Exploitation of neural network vision technologies like object detection and semantic segmentation could be a new viewpoint in this area. In this paper, we utilize an instance segmentation neural network to obtain a class mask for separately filtering the background and foreground of an image. We implement a top prior-mask selection to let us select an object class for f…
Robert Bosch GmbH（罗伯特·博世有限公司）；Goethe University Frankfurt（法兰克福歌德大学）；NTNU Trondheim（特隆赫姆挪威科技大学）
Existing 3D scene flow estimation methods provide the 3D geometry and 3D motion of a scene and gain a lot of interest, for example in the context of autonomous driving. These methods are traditionally based on a temporal series of stereo images. In this paper, we propose a novel monocular 3D scene flow estimation method, called Mono-SF. Mono-SF jointly estimates the 3D structure and motion of the scene by combining multi-view geometry and single-view depth information. Mono-SF considers that the scene flow should be consistent in terms of warping the reference image in the consecutive image ba…
Xidian University（西安电子科技大学）；West Virginia University（西弗吉尼亚大学）
State-of-the-art approaches toward image restoration can be classified into model-based and learning-based. The former - best represented by sparse coding techniques - strive to exploit intrinsic prior knowledge about the unknown high-resolution images; while the latter - popularized by recently developed deep learning techniques - leverage external image prior from some training dataset. It is natural to explore their middle ground and pursue a hybrid image prior capable of achieving the best in both worlds. In this paper, we propose a systematic approach of achieving this goal called Structu…
Wuhan University（武汉大学）；University of Central Florida（中佛罗里达大学）；Shenzhen University（深圳大学）；National Tsing Hua University（台湾清华大学）
Convolutional neural network (CNN) and Transformer have achieved great success in multimedia applications. However, little effort has been made to effectively and efficiently harmonize these two architectures to satisfy image deraining. This paper aims to unify these two architectures to take advantage of their learning merits for image deraining. In particular, the local connectivity and translation equivariance of CNN and the global aggregation ability of self-attention (SA) in Transformer are fully exploited for specific local context and global structure representations. Based on the obser…
Ryerson University（瑞尔森大学）；Vector Institute for AI（向量人工智能研究所）；York University（约克大学）；Toronto AI Lab, LG Electronics（LG电子多伦多人工智能实验室）；Samsung AI Centre Toronto（三星多伦多人工智能中心）；University of Guelph（圭尔夫大学）
In this paper, we challenge the common assumption that collapsing the spatial dimensions of a 3D (spatial-channel) tensor in a convolutional neural network (CNN) into a vector via global pooling removes all spatial information. Specifically, we demonstrate that positional information is encoded based on the ordering of the channel dimensions, while semantic information is largely not. Following this demonstration, we show the real world impact of these findings by applying them to two applications. First, we propose a simple yet effective data augmentation strategy and loss function which impr…
University of Notre Dame（圣母大学）；University of Kansas（堪萨斯大学）；Pazmany Peter Catholic University（帕兹马尼·彼得天主教大学）；Georgia Institute of Technology（佐治亚理工学院）
Deep neural network (DNN) accelerators with improved energy and delay are desirable for meeting the requirements of hardware targeted for IoT and edge computing systems. Convolutional neural networks (CoNNs) belong to one of the most popular types of DNN architectures. This paper presents the design and evaluation of an accelerator for CoNNs. The system-level architecture is based on mixed-signal, cellular neural networks (CeNNs). Specifically, we present (i) the implementation of different layers, including convolution, ReLU, and pooling, in a CoNN using CeNN, (ii) modified CoNN structures wi…
University of Technology at Sydney（悉尼科技大学）；University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）
In the early days, content-based image retrieval (CBIR) was studied with global features. Since 2003, image retrieval based on local descriptors (de facto SIFT) has been extensively studied for over a decade due to the advantage of SIFT in dealing with image transformations. Recently, image representations based on the convolutional neural network (CNN) have attracted increasing interest in the community and demonstrated impressive performance. Given this time of rapid evolution, this article provides a comprehensive survey of instance retrieval over the last decade. Two broad categories, SIFT…
CLAReSNet: When Convolution Meets Latent Attention for Hyperspectral Image Classification
Institute of Engineering and Management (IEM), University of Engineering and Management Kolkata, IEM Centre of Excellence for InnovAI, Department of Computer Science & Engineering（工程管理学院（IEM）、工程管理大学科塔卡尔，创新AI研究中心、计算机科学与工程系）；Institute of Engineering and Management (IEM), University of Engineering and Management Kolkata, Department of Computer Science & Engineering（工程管理学院（IEM）、工程管理大学科塔卡尔，计算机科学与工程系）
University of Science and Technology of China（中国科学技术大学）；UNSW Sydney（新南威尔士大学）；Genmab Inc.（Genmab公司）
NLP-based computer vision models, particularly vision transformers, have been shown to outperform CNN models in many imaging tasks. However, most digital pathology artificial-intelligence models are based on CNN architectures, probably owing to a lack of data regarding NLP models for pathology images. In this study, we developed digital pathology pipelines to benchmark the five most recently proposed NLP models (vision transformer (ViT), Swin Transformer, MobileViT, CMT, and Sequencer2D) and four popular CNN models (ResNet18, ResNet50, MobileNetV2, and EfficientNet) to predict biomarkers in co…
Freezing of gait (FOG) is a common and debilitating gait impairment in Parkinson's disease. Further insight into this phenomenon is hampered by the difficulty to objectively assess FOG. To meet this clinical need, this paper proposes an automated motion-capture-based FOG assessment method driven by a novel deep neural network. Automated FOG assessment can be formulated as an action segmentation problem, where temporal models are tasked to recognize and temporally localize the FOG segments in untrimmed motion capture trials. This paper takes a closer look at the performance of state-of-the-art …
Research & Development Institute of Northwestern Polytechnical University in Shenzhen（西北工业大学深圳研究院）；School of Automation, Northwestern Polytechnical University（西北工业大学自动化学院）；School of Computer Science, Wuhan University（武汉大学计算机学院）
Remote sensing image scene classification, which aims at labeling remote sensing images with a set of semantic categories based on their contents, has broad applications in a range of fields. Propelled by the powerful feature learning capabilities of deep neural networks, remote sensing image scene classification driven by deep learning has drawn remarkable attention and achieved significant breakthroughs. However, to the best of our knowledge, a comprehensive review of recent achievements regarding deep learning for scene classification of remote sensing images is still lacking. Considering t…
Quality control is a fundamental component of many manufacturing processes, especially those involving casting or welding. However, manual quality control procedures are often time-consuming and error-prone. In order to meet the growing demand for high-quality products, the use of intelligent visual inspection systems is becoming essential in production lines. Recently, Convolutional Neural Networks (CNNs) have shown outstanding performance in both image classification and localization tasks. In this article, a system is proposed for the identification of casting defects in X-ray images, based…
Understanding driver activity is vital for in-vehicle systems that aim to reduce the incidence of car accidents rooted in cognitive distraction. Automating real-time behavior recognition while ensuring actions classification with high accuracy is however challenging, given the multitude of circumstances surrounding drivers, the unique traits of individuals, and the computational constraints imposed by in-vehicle embedded platforms. Prior work fails to jointly meet these runtime/accuracy requirements and mostly rely on a single sensing modality, which in turn can be a single point of failure. I…
Peking University（北京大学）；The University of Tokyo（东京大学）
Vision Transformers (ViTs) have recently achieved competitive performance in broad vision tasks. Unfortunately, on popular threat models, naturally trained ViTs are shown to provide no more adversarial robustness than convolutional neural networks (CNNs). Adversarial training is still required for ViTs to defend against such adversarial attacks. In this paper, we provide the first and comprehensive study on the adversarial training recipe of ViTs via extensive evaluation of various training techniques across benchmark datasets. We find that pre-training and SGD optimizer are necessary for ViTs…
The University of Iowa（爱荷华大学）；The University of Science and Technology of China（中国科学技术大学）
Automated surface segmentation is important and challenging in many medical image analysis applications. Recent deep learning based methods have been developed for various object segmentation tasks. Most of them are a classification based approach (e.g., U-net), which predicts the probability of being target object or background for each voxel. One problem of those methods is lacking of topology guarantee for segmented objects, and usually post processing is needed to infer the boundary surface of the object. In this paper, a novel model based on 3-D convolutional neural networks (CNNs) and Co…
Carnegie Mellon University（卡内基梅隆大学）；Bosch Center for AI（博世人工智能中心）
Neural network weights are typically initialized at random from univariate distributions, controlling just the variance of individual weights even in highly-structured operations like convolutions. Recent ViT-inspired convolutional networks such as ConvMixer and ConvNeXt use large-kernel depthwise convolutions whose learned filters have notable structure; this presents an opportunity to study their empirical covariances. In this work, we first observe that such learned filters have highly-structured covariance matrices, and moreover, we find that covariances calculated from small networks may …
The provision of paratransit services is one option to meet the transportation needs of Vulnerable Road Users (VRUs). Like any other means of transportation, paratransit has obstacles such as high operational costs and longer trip times. As a result, customers are dissatisfied, and paratransit operators have a low approval rating. Researchers have undertaken various studies over the years to better understand the travel behaviors of paratransit customers and how they are operated. According to the findings of these researches, paratransit operators confront the challenge of determining the opt…
In recent years, the research community has discovered that deep neural networks (DNNs) and convolutional neural networks (CNNs) can yield higher accuracy than all previous solutions to a broad array of machine learning problems. To our knowledge, there is no single CNN/DNN architecture that solves all problems optimally. Instead, the "right" CNN/DNN architecture varies depending on the application at hand. CNN/DNNs comprise an enormous design space. Quantitatively, we find that a small region of the CNN design space contains 30 billion different CNN architectures. In this dissertation, we dev…
National University of Computer and Emerging Sciences（国立计算机与新兴科学大学）；Innopolis University（因诺波利斯大学）；University of Messina（墨西拿大学）；Jalpaiguri Government Engineering College（贾尔派古里政府工程学院）；Beijing Institute of Technology（北京理工大学）
Convolutional Neural Networks (CNN) are more suitable, indeed. However, fixed kernel sizes make traditional CNN too specific, neither flexible nor conducive to feature learning, thus impacting on the classification accuracy. The convolution of different kernel size networks may overcome this problem by capturing more discriminating and relevant information. In light of this, the proposed solution aims at combining the core idea of 3D and 2D Inception net with the Attention mechanism to boost the HSIC CNN performance in a hybrid scenario. The resulting \textit{attention-fused hybrid network} (A…
Swin Meets EfficientNet: Lightweight Architectures for GAN-Based Face Forensics
International Institute of Information Technology, Bangalore（国际信息技术学院（班加罗尔））；Ulster University（阿尔斯特大学）；Dr B R Ambedkar National Institute of Technology Jalandhar（阿姆倍伽尔博士国家技术学院贾朗达尔分校）
École Nationale Supérieure d’Informatique（国立高等信息学院）；Université Polytechnique Hauts-de-France（上法兰西理工大学）
Running Convolutional Neural Network (CNN) based applications on edge devices near the source of data can meet the latency and privacy challenges. However due to their reduced computing resources and their energy constraints, these edge devices can hardly satisfy CNN needs in processing and data storage. For these platforms, choosing the CNN with the best trade-off between accuracy and execution time while respecting Hardware constraints is crucial. In this paper, we present and compare five (5) of the widely used Machine Learning based methods for execution time prediction of CNNs on two (2) …
Tsinghua University（清华大学）；The Chinese University of Hong Kong（香港中文大学）
Lossy compression introduces complex compression artifacts, particularly blocking artifacts, ringing effects and blurring. Existing algorithms either focus on removing blocking artifacts and produce blurred output, or restore sharpened images that are accompanied with ringing effects. Inspired by the success of deep convolutional networks (DCN) on superresolution, we formulate a compact and efficient network for seamless attenuation of different compression artifacts. To meet the speed requirement of real-world applications, we further accelerate the proposed baseline model by layer decomposit…
Event cameras are bio-inspired vision sensors that naturally capture the dynamics of a scene, filtering out redundant information. This paper presents a deep neural network approach that unlocks the potential of event cameras on a challenging motion-estimation task: prediction of a vehicle's steering angle. To make the best out of this sensor-algorithm combination, we adapt state-of-the-art convolutional architectures to the output of event sensors and extensively evaluate the performance of our approach on a publicly available large scale event-camera dataset (~1000 km). We present qualitativ…
Recent work has shown that the activation function of the convolutional neural network can meet the Lipschitz condition, then the corresponding convolutional neural network structure can be constructed according to the scale of the data set, and the data set can be trained more deeply, more accurately and more effectively. In this article, we have accepted the experimental results and introduced the core block N-Gauss, N-Gauss, and Swish (Conv1, Conv2, FC1) neural network structure design to train MNIST, CIFAR10, and CIFAR100 respectively. Experiments show that N-Gauss gives full play to the m…
University of Toronto（多伦多大学）；LG AI Research（LG AI研究院）
As an emerging field in Machine Learning, Explainable AI (XAI) has been offering remarkable performance in interpreting the decisions made by Convolutional Neural Networks (CNNs). To achieve visual explanations for CNNs, methods based on class activation mapping and randomized input sampling have gained great popularity. However, the attribution methods based on these techniques provide lower resolution and blurry explanation maps that limit their explanation power. To circumvent this issue, visualization based on various layers is sought. In this work, we collect visualization maps from multi…
