The square kernel is a standard unit for contemporary CNNs, as it fits well on the tensor computation for convolution operation. However, the retinal ganglion cells in the biological visual system have approximately concentric receptive fields. Motivated by this observation, we propose to use circular kernel with a concentric and isotropic receptive field as an option for the convolution operation. We first propose a simple yet efficient implementation of the convolution using circular kernels, and empirically show the significant advantages of large circular kernels over the counterpart square kernels. We then expand the operation space of several typical Neural Architecture Search (NAS) methods with the convolutions of large circular kernels. The searched new neural architectures do contain large circular kernels and outperform the original searched models considerably. Our additional analysis also reveals that large circular kernels could help the model to be more robust to the rotated or sheared images due to their better rotation invariance. Our work shows the potential of designing new convolutional kernels for CNNs, bringing up the prospect of expanding the search space of NAS with new variants of convolutions.
We propose a method for integration of features extracted using deep representations of Convolutional Neural Networks (CNNs) each of which is learned using a different image dataset of objects and materials for material recognition. Given a set of representations of multiple pre-trained CNNs, we first compute activations of features using the representations on the images to select a set of samples which are best represented by the features. Then, we measure the uncertainty of the features by computing the entropy of class distributions for each sample set. Finally, we compute the contribution…
ADAPT Centre（ADAPT中心）；Trinity College Dublin（都柏林圣三一学院）
Convolutional neural networks (CNNs) learn filters in order to capture local correlation patterns in feature space. In contrast, in this paper we propose harmonic blocks that produce features by learning optimal combinations of spectral filters defined by the Discrete Cosine Transform. The harmonic blocks are used to replace conventional convolutional layers to construct partial or fully harmonic CNNs. We extensively validate our approach and show that the introduction of harmonic blocks into state-of-the-art CNN baseline architectures results in comparable or better performance in classificat…
Graz University of Technology（格拉茨工业大学）；Ludwig Boltzmann Institute for Clinical Forensic Imaging（路德维希·玻尔兹曼临床法医成像研究所）
In many medical image analysis applications, often only a limited amount of training data is available, which makes training of convolutional neural networks (CNNs) challenging. In this work on anatomical landmark localization, we propose a CNN architecture that learns to split the localization task into two simpler sub-problems, reducing the need for large training datasets. Our fully convolutional SpatialConfiguration-Net (SCN) dedicates one component to locally accurate but ambiguous candidate predictions, while the other component improves robustness to ambiguities by incorporating the spa…
A Dynamic Graph CNN with Cross-Representation Distillation for Event-Based Recognition
National Engineering Research Center for E-Learning, Central China Normal University（华中师范大学国家数字化学习工程技术研究中心）；Beijing University of Technology（北京工业大学）；Southeast University（东南大学）；City University of Hong Kong（香港城市大学）
INT8 quantization has become one of the standard techniques for deploying convolutional neural networks (CNNs) on edge devices to reduce the memory and computational resource usages. By analyzing quantized performances of existing mobile-target network architectures, we can raise an issue regarding the importance of network architecture for optimal INT8 quantization. In this paper, we present a new network architecture search (NAS) procedure to find a network that guarantees both full-precision (FLOAT32) and quantized (INT8) performances. We first propose critical but straightforward optimizat…
Universiti Teknologi Malaysia（马来西亚理工大学）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）
We exploit altered patterns in brain functional connectivity as features for automatic discriminative analysis of neuropsychiatric patients. Deep learning methods have been introduced to functional network classification only very recently for fMRI, and the proposed architectures essentially focused on a single type of connectivity measure. We propose a deep convolutional neural network (CNN) framework for classification of electroencephalogram (EEG)-derived brain connectome in schizophrenia (SZ). To capture complementary aspects of disrupted connectivity in SZ, we explore combination of vario…
University of Miami（迈阿密大学）；Computer Science Department（计算机科学系）；Coral Gables, FL 33146（科勒尔盖布尔斯，佛罗里达州 33146（注：这是地址，非机构，不应提取，但根据用户提供的文本，此处可能存在格式问题，原文本中“Affiliation: Coral Gables, FL 33146”可能是笔误，正确机构应为“University of Miami”下的部门，此处严格按用户提取范围，仅保留明确机构名））
Deep convolutional neural networks (CNNs) are becoming increasingly popular models to predict neural responses in visual cortex. However, contextual effects, which are prevalent in neural processing and in perception, are not explicitly handled by current CNNs, including those used for neural prediction. In primary visual cortex, neural responses are modulated by stimuli spatially surrounding the classical receptive field in rich ways. These effects have been modeled with divisive normalization approaches, including flexible models, where spatial normalization is recruited only to the degree r…
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳人工智能与机器人研究院）
Temporal convolution has been widely used for video classification. However, it is performed on spatio-temporal contexts in a limited view, which often weakens its capacity of learning video representation. To alleviate this problem, we propose a concise and novel SmallBig network, with the cooperation of small and big views. For the current time step, the small view branch is used to learn the core semantics, while the big view branch is used to capture the contextual semantics. Unlike traditional temporal convolution, the big view branch can provide the small view branch with the most activa…
VMRNN: Integrating Vision Mamba and LSTM for Efficient and Accurate Spatiotemporal Forecasting
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Hong Kong Baptist University（香港浸会大学）；The Hong Kong University of Science and Technology（香港科技大学）
The convolutional layers of standard convolutional neural networks (CNNs) are equivariant to translation. However, the convolution and fully-connected layers are not equivariant or invariant to other affine geometric transformations. Recently, a new class of CNNs is proposed in which the conventional layers of CNNs are replaced with equivariant convolution, pooling, and batch-normalization layers. The final classification layer in equivariant neural networks is invariant to different affine geometric transformations such as rotation, reflection and translation, and the scalar value is obtained…
This paper is concerned with a fundamental problem in geometric deep learning that arises in the construction of convolutional neural networks on surfaces. Due to curvature, the transport of filter kernels on surfaces results in a rotational ambiguity, which prevents a uniform alignment of these kernels on the surface. We propose a network architecture for surfaces that consists of vector-valued, rotation-equivariant features. The equivariance property makes it possible to locally align features, which were computed in arbitrary coordinate systems, when aggregating features in a convolution la…
Univ Lyon（里昂大学）；INSA‐Lyon（里昂国立应用科学学院）；Université Claude Bernard Lyon 1（里昂第一大学）；UJM-Saint Etienne（圣艾蒂安大学）；CNRS（法国国家科学研究中心）；Inserm（法国国家健康与医学研究院）；CREATIS UMR 5220（CREATIS联合研究单位5220）；U1206（U1206研究单位）
Semantic segmentation is an established while rapidly evolving field in medical imaging. In this paper we focus on the segmentation of brain Magnetic Resonance Images (MRI) into cerebral structures using convolutional neural networks (CNN). CNNs achieve good performance by finding effective high dimensional image features describing the patch content only. In this work, we propose different ways to introduce spatial constraints into the network to further reduce prediction inconsistencies. A patch based CNN architecture was trained, making use of multiple scales to gather contextual informatio…
Université Côte d’Azur（蔚蓝海岸大学）；Inria（法国国家信息与自动化研究所）；Université Paris-Sud（巴黎第十一大学）；Laboratoire de Recherche en Informatique（计算机科学研究所）
Convolutional neural networks (CNNs) have received increasing attention over the last few years. They were initially conceived for image categorization, i.e., the problem of assigning a semantic label to an entire input image. In this paper we address the problem of dense semantic labeling, which consists in assigning a semantic label to every pixel in an image. Since this requires a high spatial accuracy to determine where labels are assigned, categorization CNNs, intended to be highly robust to local deformations, are not directly applicable. By adapting categorization networks, many semanti…
Multilevel neural networks with dual-stage feature fusion for human activity recognition
Departamento de Informática, Universidad Carlos III de Madrid（信息学院，卡洛斯三世大学）；Departamento de Teoría de la Señal y Comunicaciones, Universidad Carlos III de Madrid（信号与通信理论系，卡洛斯三世大学）；CEIEC, Universidad Francisco de Vitoria（CEIEC，弗朗西斯科·维多利亚大学）
WiTUnet: A U-Shaped Architecture Integrating CNN and Transformer for Improved Feature Alignment and Local Information Fusion
College of Computer Science and Cyber Security, Chengdu University of Technology（成都理工大学计算机与网络安全学院）；College of Geophysics, Chengdu University of Technology（成都理工大学地球物理学院）；College of Mechanical and Vehicle Engineering, Changchun University（长春大学机械与车辆工程学院）
Peking University（北京大学）；Intellifusion（云天励飞）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
Transformers have shown great potential in various computer vision tasks. By borrowing design concepts from transformers, many studies revolutionized CNNs and showed remarkable results. This paper falls in this line of studies. Specifically, we propose a new convolutional neural network, ParCNetV2, that extends position-aware circular convolution (ParCNet) with oversized convolutions and bifurcate gate units to enhance attention. The oversized convolution employs a kernel with twice the input size to model long-range dependencies through a global receptive field. Simultaneously, it achieves im…
William & Mary（威廉玛丽学院）；Northeastern University（东北大学）；North Carolina State University（北卡罗来纳州立大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
Mobile devices are becoming an important carrier for deep learning tasks, as they are being equipped with powerful, high-end mobile CPUs and GPUs. However, it is still a challenging task to execute 3D Convolutional Neural Networks (CNNs) targeting for real-time performance, besides high inference accuracy. The reason is more complex model structure and higher model dimensionality overwhelm the available computation/storage resources on mobile devices. A natural way may be turning to deep learning weight pruning techniques. However, the direct generalization of existing 2D CNN weight pruning me…
Attention-Guided Fusion of 1D and 2D CNNs for Robust ECG-Based Biometric Recognition
PIMIS Laboratory, Electronics and Telecommunications Department（PIMIS实验室，电子与电信系）；Université du 8 Mai 1945（8月1945大学）；Electrical Engineering Department, University of 20 August 1955（电子工程系，20 August 1955大学）；Department of Electrical Engineering, Faculty of Science and Applied Sciences（电子工程系，科学与应用科学学院）；Larbi Ben M'hidi University（拉比·本·迈迪大学）；Department of Electronics and Communications, University of Larbi Tebessi（电子与通信系，拉比·塔贝西大学）
Convolutional neural networks (CNNs) are inherently suffering from massively redundant computation (FLOPs) due to the dense connection pattern between feature maps and convolution kernels. Recent research has investigated the sparse relationship between channels, however, they ignored the spatial relationship within a channel. In this paper, we present a novel convolutional operator, namely comb convolution, to exploit the intra-channel sparse relationship among neurons. The proposed convolutional operator eliminates nearly 50% of connections by inserting uniform mappings into standard convolu…
Improved Prognostic Prediction of Pancreatic Cancer Using Multi-Phase CT by Integrating Neural Distance and Texture-Aware Transformer
DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；Peking University（北京大学）；Hupan Lab（湖畔实验室）；Sun Yat-sen University Cancer Center（中山大学肿瘤防治中心）；South China Hospital, Shenzhen University（深圳大学华南医院）；Tianjin Medical University Cancer Institute and Hospital（天津医科大学肿瘤医院）；Changsha Institute for Computing and Digital Economy（长沙计算与数字经济研究院）；Guangdong Provincial People’s Hospital（广东省人民医院）；Shengjing Hospital（盛京医院）
