Convolutional neural networks excel in a number of computer vision tasks. One of their most crucial architectural elements is the effective receptive field size, that has to be manually set to accommodate a specific task. Standard solutions involve large kernels, down/up-sampling and dilated convolutions. These require testing a variety of dilation and down/up-sampling factors and result in non-compact representations and excessive number of parameters. We address this issue by proposing a new convolution filter composed of displaced aggregation units (DAU). DAUs learn spatial displacements and adapt the receptive field sizes of individual convolution filters to a given problem, thus eliminating the need for hand-crafted modifications. DAUs provide a seamless substitution of convolutional filters in existing state-of-the-art architectures, which we demonstrate on AlexNet, ResNet50, ResNet101, DeepLab and SRN-DeblurNet. The benefits of this design are demonstrated on a variety of computer vision tasks and datasets, such as image classification (ILSVRC 2012), semantic segmentation (PASCAL VOC 2011, Cityscape) and blind image de-blurring (GOPRO). Results show that DAUs efficiently allocate parameters resulting in up to four times more compact networks at similar or better performance.
Spatially-Adaptive Filter Units for Deep Neural Networks
Faculty of Computer and Information Science, University of Ljubljana（卢布尔雅那大学计算机与信息科学学院）；CN-CR Centre, School of Computer Science, University of Birmingham（伯明翰大学计算机学院CN-CR中心）
联合图像滤波器用于在诸如提高空间分辨率和抑制噪声的任务中从用作目标图像之前的引导图像传递结构细节。基于卷积神经网络（CNN）的先前方法结合空间不变核的非线性激活来估计结构细节并回归滤波结果。在本文中，我们学习显式稀疏和空间变化的内核。我们提出了一个CNN架构及其有效的实现，称为变形核网络（DKN），输出的邻居和相应的权重集自适应每个像素。然后将滤波结果计算为加权平均。我们还提出了一个快速版本的DKN，运行速度约为17倍的大小为640 x 480的图像。我们证明了我们的模型在深度图上采样，显着图上采样，跨模态图像复原，纹理去除和语义分割的任务的有效性和灵活性。特别是，我们表明，稀疏采样的3 × 3内核的加权平均过程在所有情况下都优于最先进的显着保证金。
Adaptive Local Frequency Filtering for Fourier-Encoded Implicit Neural Representations
College of Computer Science (College of Software), Inner Mongolia University（内蒙古大学计算机科学学院（软件学院））；Institute of Computational Imaging, Beijing Information Science and Technology University（北京信息科技大学计算成像研究所）；School of Mathematics and Statistics, Wuhan University（武汉大学数学与统计学院）
LMLCC-Net: A Semi-Supervised Deep Learning Model for Lung Nodule Malignancy Prediction from CT Scans using a Novel Hounsfield Unit-Based Intensity Filtering
mHealth Lab, Department of Biomedical Engineering, Bangladesh University of Engineering and Technology（孟加拉国工程与技术大学生物医学工程系mHealth实验室）
Spatially Covariant Image Registration with Text Prompts
College of Electrical and Information Engineering, Hunan University（湖南大学电气与信息工程学院）；Cornell University（康奈尔大学）；University of Pennsylvania（宾夕法尼亚大学）；New York University（纽约大学）；Shanghai Jiao Tong University（上海交通大学）
