中文
相关论文

相关论文: Land cover mapping at very high resolution with ro…

200 篇论文

Self-supervised image denoising methods have garnered significant research attention in recent years, for this kind of method reduces the requirement of large training datasets. Compared to supervised methods, self-supervised methods rely…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Hanze Liu , Jiahong Fu , Qi Xie , Deyu Meng

Despite the importance of image representations such as histograms of oriented gradients and deep Convolutional Neural Networks (CNN), our theoretical understanding of them remains limited. Aiming at filling this gap, we investigate three…

计算机视觉与模式识别 · 计算机科学 2015-06-23 Karel Lenc , Andrea Vedaldi

Detecting robust keypoints from an image is an integral part of many computer vision problems, and the characteristic orientation and scale of keypoints play an important role for keypoint description and matching. Existing learning-based…

计算机视觉与模式识别 · 计算机科学 2022-04-20 Jongmin Lee , Byungjin Kim , Minsu Cho

In this paper, we introduce group convolutional neural networks (GCNNs) equivariant to color variation. GCNNs have been designed for a variety of geometric transformations from 2D and 3D rotation groups, to semi-groups such as scale.…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Yulong Yang , Felix O'Mahony , Christine Allen-Blanchette

Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance on many visual recognition tasks. However, the combination of convolution and pooling operations only shows invariance to small local location changes in…

计算机视觉与模式识别 · 计算机科学 2019-12-02 Xu Shen , Xinmei Tian , Shaoyan Sun , Dacheng Tao

In the recent application of scientific modeling, machine learning models are largely applied to facilitate computational simulations of fluid systems. Rotation symmetry is a general property for most symmetric fluid systems. However, in…

计算工程、金融与科学 · 计算机科学 2020-05-12 Liyao Gao , Yifan Du , Hongshan Li , Guang Lin

Equivariance of neural networks to transformations helps to improve their performance and reduce generalization error in computer vision tasks, as they apply to datasets presenting symmetries (e.g. scalings, rotations, translations). The…

计算机视觉与模式识别 · 计算机科学 2022-11-08 Mateus Sangalli , Samy Blusseau , Santiago Velasco-Forero , Jesus Angulo

Training a Convolutional Neural Network (CNN) to be robust against rotation has mostly been done with data augmentation. In this paper, another progressive vision of research direction is highlighted to encourage less dependence on data…

计算机视觉与模式识别 · 计算机科学 2021-10-22 Sungwon Hwang , Hyungtae Lim , Hyun Myung

Recently, object detection in aerial images has gained much attention in computer vision. Different from objects in natural images, aerial objects are often distributed with arbitrary orientation. Therefore, the detector requires more…

计算机视觉与模式识别 · 计算机科学 2021-03-16 Jiaming Han , Jian Ding , Nan Xue , Gui-Song Xia

Objects in aerial images have greater variations in scale and orientation than in typical images, so detection is more difficult. Convolutional neural networks use a variety of frequency- and orientation-specific kernels to identify objects…

计算机视觉与模式识别 · 计算机科学 2021-11-08 Guo-Ye Yang , Xiang-Li Li , Ralph R. Martin , Shi-Min Hu

The weight-sharing mechanism of convolutional kernels ensures translation-equivariance of convolution neural networks (CNNs). Recently, rotation-equivariance has been investigated. However, research on scale-equivariance or simultaneous…

计算机视觉与模式识别 · 计算机科学 2023-06-13 Wei-Dong Qiao , Yang Xu , Hui Li

When seeing a new object, humans can immediately recognize it across different retinal locations: we say that the internal object representation is invariant to translation. It is commonly believed that Convolutional Neural Networks (CNNs)…

计算机视觉与模式识别 · 计算机科学 2020-11-25 Valerio Biscione , Jeffrey Bowers

Rotation invariance has been studied in the computer vision community primarily in the context of small in-plane rotations. This is usually achieved by building invariant image features. However, the problem of achieving invariance for…

计算机视觉与模式识别 · 计算机科学 2016-11-18 Lokesh Boominathan , Suraj Srinivas , R. Venkatesh Babu

The translation equivariance of convolutions can make convolutional neural networks translation equivariant or invariant. Equivariance to other transformations (e.g. rotations, affine transformations, scalings) may also be desirable as soon…

信号处理 · 电气工程与系统科学 2021-05-05 Mateus Sangalli , Samy Blusseau , Santiago Velasco-Forero , Jesus Angulo

CNNs exhibit inherent equivariance to image translation, leading to efficient parameter and data usage, faster learning, and improved robustness. The concept of translation equivariant networks has been successfully extended to rotation…

计算机视觉与模式识别 · 计算机科学 2024-11-07 Tomáš Karella , Adam Harmanec , Jan Kotera , Jan Blažek , Filip Šroubek

In the task of Object Recognition, there exists a dichotomy between the categorization of objects and estimating object pose, where the former necessitates a view-invariant representation, while the latter requires a representation capable…

计算机视觉与模式识别 · 计算机科学 2016-04-20 Mohamed Elhoseiny , Tarek El-Gaaly , Amr Bakry , Ahmed Elgammal

Encoding the scale information explicitly into the representation learned by a convolutional neural network (CNN) is beneficial for many computer vision tasks especially when dealing with multiscale inputs. We study, in this paper, a…

机器学习 · 计算机科学 2022-02-08 Wei Zhu , Qiang Qiu , Robert Calderbank , Guillermo Sapiro , Xiuyuan Cheng

Performance of neural networks can be significantly improved by encoding known invariance for particular tasks. Many image classification tasks, such as those related to cellular imaging, exhibit invariance to rotation. We present a novel…

机器学习 · 统计学 2018-06-01 Benjamin Chidester , Minh N. Do , Jian Ma

In Reinforcement Learning (RL), Convolutional Neural Networks(CNNs) have been successfully applied as function approximators in Deep Q-Learning algorithms, which seek to learn action-value functions and policies in various environments.…

机器学习 · 计算机科学 2020-07-08 Arnab Kumar Mondal , Pratheeksha Nair , Kaleem Siddiqi

The principle of equivariance to symmetry transformations enables a theoretically grounded approach to neural network architecture design. Equivariant networks have shown excellent performance and data efficiency on vision and medical…

机器学习 · 计算机科学 2019-05-15 Taco S. Cohen , Maurice Weiler , Berkay Kicanaoglu , Max Welling