polynomial learnable networks optimal
U-Net: Convolutional Networks for Biomedical Image Segmentation
U-Net: Convolutional Networks for Biomedical Image Segmentation * Authors: [[Olaf Ronneberger]], [[Philipp Fischer]], [[Thomas Brox]] Local library 初读 ......
Non-local Neural Networks 第一次将自注意力用于cv
Non-local Neural Networks * Authors: [[Xiaolong Wang]], [[Ross Girshick]], [[Abhinav Gupta]], [[Kaiming He]] Local library 初读印象 comment:: (NonLocal)过去 ......
RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation
RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation * Authors: [[Guosheng Lin]], [[Anton Milan]], [[Chunhua Shen]], [[ ......
Expectation-Maximization Attention Networks for Semantic Segmentation 使用了EM算法的注意力
Expectation-Maximization Attention Networks for Semantic Segmentation * Authors: [[Xia Li]], [[Zhisheng Zhong]], [[Jianlong Wu]], [[Yibo Yang]], [[Zho ......
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network * Authors: [[Wenzhe Shi]], [[Jose Caballer ......
Pyramid Scene Parsing Network
Pyramid Scene Parsing Network * Authors: [[Hengshuang Zhao]], [[Jianping Shi]], [[Xiaojuan Qi]], [[Xiaogang Wang]], [[Jiaya Jia]] DOI: 10.1109/CVPR.20 ......
Asymmetric Non-Local Neural Networks for Semantic Segmentation 非对称注意力
Asymmetric Non-Local Neural Networks for Semantic Segmentation * Authors: [[Zhen Zhu]], [[Mengdu Xu]], [[Song Bai]], [[Tengteng Huang]], [[Xiang Bai]] ......
PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers
PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers * Authors: [[Jiacong Xu]], [[Zixiang Xiong]], [[Shankar P. Bhattacharyya ......
PSANet: Point-wise Spatial Attention Network for Scene Parsing双向注意力
PSANet: Point-wise Spatial Attention Network for Scene Parsing * Authors: [[Hengshuang Zhao]], [[Yi Zhang]], [[Shu Liu]], [[Jianping Shi]], [[Chen Cha ......
Object Tracking Network Based on Deformable Attention Mechanism
Object Tracking Network Based on Deformable Attention Mechanism Local library 初读印象 comment:: （DeTrack）采用基于可变形注意力机制的编码器模块和基于自注意力机制的编码器模块相结合的方式进行特征交互。基于 ......
Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images
Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images * Authors: [[Bowei Du]], [[Yecheng ......
A Deformable Attention Network for High-Resolution Remote Sensing Images Semantic Segmentation可变形注意力
A Deformable Attention Network for High-Resolution Remote Sensing Images Semantic Segmentation * Authors: [[Renxiang Zuo]], [[Guangyun Zhang]], [[Rong ......
SiReN Sign-Aware Recommendation Using Graph Neural Networks论文阅读笔记
Abstract 目前使用GNN的推荐系统主要利用高评分的正向用户-物品交互信息。但是如何利用低评分来表示用户的偏好是一个挑战，因为低评分仍然可以提供有用的信息。所以在本文中提出了基于GNN模型的有符号感知推荐系统SiReN，SiReN有三个关键组件 构造一个符号二部图更精确的表示用户的偏好，分为两 ......
Fully Attentional Network for Semantic Segmentation：FLANet
Fully Attentional Network for Semantic Segmentation * Authors: [[Qi Song]], [[Jie Li]], [[Chenghong Li]], [[Hao Guo]], [[Rui Huang]] 初读印象 comment:: (F ......
《convex optimization》——Stanford University open class
20231215 1. Introduction mathematical optimization least-squares and linear programing convex optimization exapmle course goals and topics nonlinear o ......
PANE-GNN Unifying Positive and Negative Edges in Graph Neural Networks for Recommendation论文阅读笔记
Abstract 目前利用GNN的推荐系统主要关注用户的正面反馈，而忽略了负面反馈提供的见解。于是我们提出了PANG- GNN，该模型将图神经网络的正面和负面边统一在一起。PANG-GNN首先将原始评分图根据正面和负面反馈划分为两个不同的二分图。接下来分别使用两个独立的嵌入，即感兴趣嵌入和无兴趣嵌入 ......
CentOS7配置静态ip后service network restart失败
解决方法： 1、检查配置文件，文件夹下是否存在类似文件（ifcfg-ens33），存在的话，删除掉，保留一个即可（判断方式为配置文件中是否有配置信息） cd /etc/sysconfig/network-scripts/ ls 删除命令： rm 文件名称 重启网络：service network r ......
Machine is not on the network
在调试Android jni 的时候发现一个奇怪的问题 在连接socket的时候老是报错 m_sock = socket(AF_INET, SOCK_STREAM, 0); if(m_sock < 0) { debug(LEVEL_ERROR, "Socket create error %d\r\n ......
使用yarn安装依赖包出现“There appears to be trouble with your network connection. Retrying...”超时的提醒
我们在使用yarn安装依赖包文件的时候，可能会出现“There appears to be trouble with your network connection. Retrying...”超时的提醒，很有可能是因为yarn默认的镜像地址为国外，因此慢（超时）就说得过去了…… 1、问题描述 我们在 ......
0x02 Network Services
Task1、引言 这个房间将探讨常见的网络服务漏洞和错误配置。 Task2、了解SMB 什么是SMB？ SMB - 服务器消息块协议 - 是一种客户端-服务器通信协议，用于共享对网络上的文件、打印机、串行端口和其他资源的访问。[source] SMB 协议被称为响应请求协议，这意味着它在客户端和服务 ......
yarn按照依赖的时候报 info There appears to be trouble with your network connection. Retrying...
出现这个提示多数情况下是有使用代理软件的结果，我们只需要关闭代理即可1. 更换yarn镜像 yarn config set registry https://registry.npm.taobao.org 2.移除原代理 yarn config delete proxy ......
ClickHouse中select final和optimize table final的区别
ClickHouse中select final和optimize table final的区别 使用 OPTIMIZE TABLE FINAL 该语句会对表的数据部分进行计划外的合并，通常不建议使用。见官档：传送门 而在select中当 FINAL 被指定，ClickHouse会在返回结果之前完全合 ......
CodeForces 1508F Optimal Encoding
洛谷传送门 CF 传送门 考虑暴力，就是对于一对满足 \(a_u < a_v\) 的边 \(u \to v\)，如果任意一个区间包含 \([\min(u, v), \max(u, v)]\)，就将 \(u \to v\) 加入 DAG，然后做 P6134 [JSOI2015] 最小表示，就是判断是否 ......
论文精读：STMGCN利用时空多图卷积网络进行移动边缘计算驱动船舶轨迹预测（STMGCN: Mobile Edge Computing-Empowered Vessel Trajectory Prediction Using Spatio-Temporal Multigraph Convolutional Network）
《STMGCN: Mobile Edge Computing-Empowered Vessel Trajectory Prediction Using Spatio-Temporal Multigraph Convolutional Network》 论文链接：https://doi.org/10. ......
论文精读：基于具有时空感知的稀疏多图卷积混合网络的大数据驱动船舶轨迹预测（Big data driven trajectory prediction based on sparse multi-graph convolutional hybrid network withspatio-temporal awareness）
论文精读：基于具有时空感知的稀疏多图卷积混合网络的大数据驱动船舶轨迹预测 《Big data driven vessel trajectory prediction based on sparse multi-graph convolutional hybrid network with spati ......
Retentive Networks Meet Vision Transformers， 视觉RetNet
alias: Fan2023 tags: RetNet rating: ⭐ share: false ptype: article RMT: Retentive Networks Meet Vision Transformers 初读印象 comment:: (RMT)Retentive Netwo ......
How to Use Docker and NS-3 to Create Realistic Network Simulations
https://insights.sei.cmu.edu/blog/how-to-use-docker-and-ns-3-to-create-realistic-network-simulations/ How to Use Docker and NS-3 to Create Realistic N ......
[ARC164E] Segment-Tree Optimization 题解
题目链接 题目链接 题目解法 一个自认为比较自然的解法 这种一段序列切成两部分的问题首先考虑区间 \(dp\) 令 \(f_{l,r}\) 为 \([l,r]\) 能构成的最小深度，\(g_{l,r}\) 为在 \(f_{l,r}\) 最小的情况下最少的最大深度的点的个数 转移枚举 \(k\) 即可 ......
A novel essential protein identification method based on PPI networks and gene expression data
A novel essential protein identification method based on PPI networks and gene expression data Jiancheng Zhong 1 2, Chao Tang 1, Wei Peng 3, Minzhu Xi ......
A Novel Approach Based on Bipartite Network Recommendation and KATZ Model to Predict Potential Micro-Disease Associations
A Novel Approach Based on Bipartite Network Recommendation and KATZ Model to Predict Potential Micro-Disease Associations Shiru Li 1, Minzhu Xie 1, Xi ......