论文研读
文章平均质量分 86
Always_ease
这个作者很懒,什么都没留下…
展开
-
Federated Learning 联邦学习概述及最新工作
一、目前主流的联邦学习应用场景 Cross-silo FL Cross-device FL Setting Training a model on siloed data. Clients are from different organizations (e.g. medical or financial) or geo-distributed datacenters. The cli.原创 2021-06-15 17:02:07 · 1499 阅读 · 0 评论 -
【论文研读】Data Augmentation, Network Invariances, Pre-training with Hard Examples
Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation (arxiv 2020.12)idea:perform a systematic study of the Copy-Paste augmentation (e.g., [13, 12]) for instance segmentation where we randomly paste objects onto an image we原创 2021-01-03 19:17:32 · 290 阅读 · 0 评论 -
【论文研读】 两篇公众号文章;Test-Time Training;超分Domain Adaptive
测试集没有标签,我们可以拿来测试模型吗?Paper Link:https://arxiv.org/abs/2007.02915重点研究自动模型评估(AutoEval)这一重要的且尚未开发的问题。具体来说,给定带标签的训练集和分类器,我们需要估计出分类器在未标记的测试数据集上的分类准确性。 方法的出发点:测试集合和训练集合数据分布差异越大,那么分类器在测试集合上的准确率就会越低。 采用回归模型:输入为一个测试集与数据分布差异相关的特征(如均值和协方差),输出为分类器在其上的准确率。 构造元数据集原创 2020-12-18 16:30:02 · 1806 阅读 · 1 评论 -
【论文研读】Similarity of Neural Network Representations Revisited (ICML2019)
Title:Similarity of Neural Network Representations Revisited (ICML2019)Author:Simon Kornblith ...(Long Beach, California)目录Aim:invariance properties of similarity indexes 分为三个方面Comparing Similarity StructuresRelated Similarity IndexesResults.原创 2020-12-09 15:01:53 · 1875 阅读 · 3 评论 -
ECCV 2020 workshop self-supervision note
Self Supervised Learning: What is Next?一、Perspectives on Unsupervised Representation LearningSimCLR seems to benefit from deep models and long training more than SL how we handle the weight initialization may play a big role in the final features We原创 2020-11-02 15:44:25 · 225 阅读 · 2 评论 -
【论文研读】Ultrasound related paper (multi-task, detection)
Less is More: Simultaneous View Classifification and Landmark Detection for AbdominalUltrasound ImagesAuthor:Zhoubing Xu,...,Shaohua Zhouidea:提出了一个多任务框架:1)超声视图分类,2)腹部长短抽的landmark detection网络框架: Encoder:ResNet50。The first convolutional layer is m..原创 2020-08-31 15:42:39 · 315 阅读 · 0 评论 -
Self-supervised and unsupervised learning for video
ActBERT: Learning Global-Local Video-Text Representations(cvpr2020)背景:在教做菜的视频中,视频创作者会描述,“开始切胡萝卜”,往往人物也是在正进行“切胡萝卜”的动作。这种天然的视觉对应关系,是进行视频文字自监督学习的重要要素。其中文字描述可以通过自动语音识别技术(ASR)从视频中或从创作者上传的字幕中提取文字。这样成对的视频文字数据就产生了。 为了解决视觉特征无法做分类预测的问题,VideoBERT 使用了 hierachica.原创 2020-08-10 19:39:14 · 721 阅读 · 0 评论 -
【论文研读】Obscuring Surface Anatomy + Detection of Wrong-Patient when Include Patient Photographs
Obscuring Surface Anatomy in Volumetric Imaging DataAuthor: Mikhail Milchenko and Daniel Marcusidea: we developed a method of anatomical surface modification and investigated the effects of such modification on image statistics and common neuroimaging原创 2020-08-04 22:22:51 · 223 阅读 · 0 评论 -
【论文研读】Self-supervised、unsupervised learning (2020最新论文)
Are Labels Necessary for Neural Architecture SearchAuthor:Chenxi Liu ,...,Kaiming He(Facebook AI)发现: the architecture rankings produced with and without labels are highly correlated.NAS和UnNAS的结果具有高度相关性 using unlabeled images from a large d..原创 2020-07-16 17:01:23 · 2212 阅读 · 0 评论 -
论文研读:CVPR2020 相关文章
What Can Be Transferred: Unsupervised Domain Adaptation forEndoscopic Lesions Segmentation(cvpr2020)Author:Jiahua Dong,...,Xiaowei Xu问题:迁移的时候对所有信息同等对待,有些信息会损耗目标网络。how to automatically capture transferable visual characterizations and semantic represe..原创 2020-06-20 16:32:51 · 1152 阅读 · 1 评论 -
【系列论文研读】Semi-supervised learning:VAT,TEM,S4L,UDA
一、Virtual Adversarial Training (VAT)原文:Virtual adversarial training: a regularization method for supervised and semi-supervised learning.(2018PAMI)作者:T. Miyato, S.-i. Maeda (Kyoto University, Kyot...原创 2020-03-31 20:42:33 · 1823 阅读 · 5 评论 -
【论文研读】Self-supervised:AMDIM, DIM
Title:Learning deep representations by mutual information estimation and maximization(2019ICLR)Author:R Devon Hjelm(MSR Montreal)Method:主要使用最大化互信息的思想,同一张图的局部特征和全局特征应高度相关,另一张的局部特征不相关。采用NCEloss得到s...原创 2020-02-20 14:12:58 · 3816 阅读 · 0 评论 -
【论文研读】SimCLR Google2020.2提出最新自监督方法
Title:A Simple Framework for Contrastive Learning of Visual RepresentationsAuthor:Ting Chen, Geoffrey Hinton... (Google Research)参考:Hinton组力作:ImageNet无监督学习最佳性能一次提升7%,媲美监督学习网络结构Data aug...原创 2020-02-19 15:57:15 · 5301 阅读 · 0 评论 -
【论文系列研读】Superpixel: SLIC+SNN
1、SLIC(PAMI2012)Title:SLIC Superpixels Compared to State-of-the-art Superpixel MethodsAuthor:Radhakrishna Achanta ... (École Polytechnique Fédérale de Lausanne,EPFL 瑞士联邦理工学院)Other Algorithms ...原创 2020-02-15 15:34:30 · 728 阅读 · 3 评论 -
【系列论文研读】Pose Estimation
Human Pose Estimation一、Definition:defined as the problem of localization of human joints challenges of this problem – strong articulations, small and barely visible joints二、Two methods:To...原创 2019-10-29 20:26:10 · 1071 阅读 · 0 评论 -
【cvpr2019】Bag of Tricks for Image Classification with Convolutional Neural Networks
Bag of Tricks for Image Classification with Convolutional Neural Networks作者:Tong He, Zhi Zhang, Hang Zhang, Zhongyue Zhang, Junyuan Xie, Mu Li论文链接:https://arxiv.org/abs/1812.01187源码链接:https://gith...原创 2019-04-10 17:31:21 · 1482 阅读 · 3 评论 -
【论文研读】A Network Architecture for Point Cloud Classification via Automatic Depth Images Generation
论文:A Network Architecture for Point Cloud Classification via Automatic Depth Images Generation(cvpr2018)Autuor: Riccardo Roveri, Lukas Rahmann, A. Cengiz Oztireli, Markus Gross11苏黎世联邦理工学院 ¨2Disn...原创 2018-12-14 16:50:00 · 605 阅读 · 0 评论 -
【论文学习】Face Verification Using Deep Belief Networks
Icpr2016Dong-Han Jhuang, Daw-Tung Lin∗, and Chi-Hung Tsai——National Taipei University任务:识别出一张人脸,有没有这个人脸三步骤:1、 feature extraction phase: range filtering:提取ROI,如把人脸从图像...原创 2018-12-06 17:21:47 · 270 阅读 · 0 评论 -
【论文学习】PointNet++
Author:Charles R. Qi Li Yi Hao Su Leonidas J. Guibas Stanford University会议:Conference on Neural Information Processing Systems (NIPS) 2017一、回顾PointNet原理:1、learn a spatial en...原创 2018-12-05 14:47:50 · 726 阅读 · 2 评论 -
【论文学习】零样本学习:Zero-Shot learning(2018CVPR)
1、简介见过和没见过的类别都要提供类别描述信息(比如用户定义的属性标注、类别的文本描述、类别名的词向量等);某些描述信息是各个类别共有的。这些描述信息通常被称为辅助信息或语义表征。典型 ZSL 方法的一个通用假设是:存在一个共有的嵌入空间,其中有一个映射函数:定义这个函数的目的是对于见过或没见过的类别,衡量图像特征 φ(x) 和语义表征 ψ(y) 之间的相容性(compatibil...原创 2018-11-09 19:31:36 · 3604 阅读 · 2 评论 -
【论文研读】PointGrid(2018cvpr,point cloud)
Autuor:Truc Le and Ye Duan——University of MissoruriIntroduction作者提出PointGrid,这是一个三维卷积网络, 它是点和网格的集成,是一种可以更好地表示局部几何形状细节的混合模型在每一个grid cell,保持points num=K(作者选取16*16*16,对比VNet的64*64*64小多了)比现有的方法...原创 2018-12-13 16:43:55 · 1787 阅读 · 5 评论 -
【cvpr2018】Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learning(自监督)
解决问题:Learning visual features from unlabeled image data a new approach in which the number of configurations can be arbitrarily large while the number of parameters remains unchanged.相关工作:聚类...原创 2019-07-05 10:44:12 · 1085 阅读 · 0 评论 -
【系列论文研读】Self-supervised learning:rotating,M&M tuning,Jigsaw++
Self-supervised Spatiotemporal Feature Learning by Video Geometric Transformations处理数据:video 方法: a set of pre-designed geometric transformations (e.g. rotating 0°, 90°, 180°, and 270°) are applied...原创 2019-07-10 15:39:55 · 2336 阅读 · 0 评论 -
【论文研读】Category-level Adversaries for Semantics Consistent Domain Adaptation(cvpr2019)
原文链接:Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation作者:Yawei Luo , Liang Zheng,Tao Guan , Junqing Yu , Yi Yang一、背景知识介绍1、语义分割:1)定义:给...原创 2019-04-18 10:39:52 · 1577 阅读 · 0 评论