/images/avatar.webp

Yuexin

Undergraduate Student of Artificial Intelligence 😊

KEEP WALKING

机器学习算法总结

1 线性回归与逻辑回归线性回归和逻辑回归是 2 种经典的算法:一文看懂线性回归(3个优缺点+8种方法评测) - easyAI 人工智能知识库 二者的一些区别: 线性回

关于MLP的一些观点和一些未来可能的方向 【Can Attention Enable MLPs To Catch Up With CNNs】

标题 Can Attention Enable MLPs To Catch Up With CNNs 年份: 2021 年 5 月 GB/T 7714: Guo M H, Liu Z N, Mu T J, et al. Can Attention Enable MLPs To Catch Up With CNNs?[J]. arXiv preprint arXiv:2105.15078, 2021. 1 引入这是真的吗? 2021年5月的第一周,来自四个不

Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks

标题 Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks 年份: 2021 年 5 月 GB/T 7714: Guo M H, Liu Z N, Mu T J, et al. Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks[J]. arXiv preprint arXiv:2105.02358, 2021. 原作者:国孟昊 清华大学 工学博士在读 "

Swin Transformer论文解读与源码分析

标题 Swin Transformer: Hierarchical Vision Transformer using Shifted Windows 年份: 2021 年 3 月 GB/T 7714: [1] Liu Z , Lin Y , Cao Y , et al. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows[J]. 2021. Swin Transformer ( Shifted window) , 它可以作为计算机视觉的通用骨干。它基本上是一个层

Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation

标题 Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation 年份: 2021 年 5 月 GB/T 7714: Cao H, Wang Y, Chen J, et al. Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation[J]. arXiv preprint arXiv:2105.05537, 2021. 首个基于纯Transformer的U-Net形的医学图像分割网

RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition

标题 RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition 年份: 2021 年 5 月 GB/T 7714: Ding X, Zhang X, Han J, et al. RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition[J]. arXiv preprint arXiv:2105.01883, 2021. 本文是清华大学&旷视科技在结构重参数领域继ACNe

【多层感知机混合器】MLP-Mixer: An all-MLP Architecture for Visio

标题 MLP-Mixer: An all-MLP Architecture for Visio 年份: 2021 年 5 月 GB/T 7714: Tolstikhin I, Houlsby N, Kolesnikov A, et al. MLP-Mixer: An all-MLP architecture for vision[J]. arXiv preprint arXiv:2105.01601, 2021. 在这篇文章中,主要证明了卷积和注意力对于良好的性能都是足够的,但它们都

Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection

标题 Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection 年份: 2020 年 10 月 GB/T 7714: [1] Tabelini L , Berriel R , Paixo T M , et al. Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection[J]. 2020. 1 摘要本文提出了LaneATT:一种基于锚点的深车

LaneAF: Robust Multi-Lane Detection with Affinity Fields

标题 LaneAF: Robust Multi-Lane Detection with Affinity Fields 年份: 2021 年 3 月 GB/T 7714: Abualsaud H, Liu S, Lu D, et al. LaneAF: Robust Multi-Lane Detection with Affinity Fields[J]. arXiv preprint arXiv:2103.12040, 2021. 具有亲和力域的鲁棒多车道检测1 摘要本研究提出了一种涉及二值分割掩码

Deep Learning for Automatically Detecting Sidewalk Accessibility Problems Using Streetscape Imagery

标题 Deep Learning for Automatically Detecting Sidewalk Accessibility Problems Using Streetscape Imagery 年份: 2019 年 10 月 GB/T 7714: [1] Weld G, Jang E, Li A, et al. Deep Learning for Automatically Detecting Sidewalk Accessibility Problems Using Streetscape Imagery[C]. The 21st International ACM SIGACCESS Conference on Computers and Accessibility, 2019: 196–209. 1 概述最近的研究已