同步wx订阅号(arXiv每日论文速递),支持后台回复'search 关键词'查询相关的最新论文。有些许帮助的话,麻烦关注一下哦(* ̄rǒ ̄)
cs.CV 方向,今日共计33篇
[检测分类相关]:
【1】 A Novel Deep Learning Pipeline for Retinal Vessel Detection in Fluorescein Angiography
一种用于荧光素血管造影检测视网膜血管的新型深度学习流水线
作者: Li Ding, Gaurav Sharma
链接:https://arxiv.org/abs/1907.02946
【2】 Benchmarking unsupervised near-duplicate image detection
基准无监督近重复图像检测
作者: Lia Morra, Fabrizio Lamberti
链接:https://arxiv.org/abs/1907.02821
【3】 AI-based evaluation of the SDGs: The case of crop detection with earth observation data
基于人工智能的可持续发展目标评估:利用地球观测数据进行作物检测的案例
作者: Natalia Efremova, Dmitry Zausaev
链接:https://arxiv.org/abs/1907.02813
【4】 Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions
基于类条件胶囊重构的对抗性图像检测与诊断
作者: Yao Qin, Geoffrey Hinton
链接:https://arxiv.org/abs/1907.02957
【5】 Structure fusion based on graph convolutional networks for semi-supervised classification
基于图卷积网络的半监督分类结构融合
作者: Guangfeng Lin, Wanjun Chen
链接:https://arxiv.org/abs/1907.02586
【6】 DeepAAA: clinically applicable and generalizable detection of abdominal aortic aneurysm using deep learning
DeepAAA:使用深度学习对腹主动脉瘤进行临床适用和可推广的检测
作者: Jen-Tang Lu, Neil A. Tenenholtz
备注:Accepted for publication at MICCAI 2019
链接:https://arxiv.org/abs/1907.02567
[分割/语义相关]:
【1】 Self-Supervised Learning for Cardiac MR Image Segmentation by Anatomical Position Prediction
基于解剖位置预测的心脏MR图像分割的自监督学习
作者: Wenjia Bai, Daniel Rueckert
备注:Accepted by MICCAI 2019
链接:https://arxiv.org/abs/1907.02757
【2】 A Spectral Approach to Unsupervised Object Segmentation in Video
一种用于视频中无监督对象分割的谱方法
作者: Elena Burceanu, Marius Leordeanu
链接:https://arxiv.org/abs/1907.02731
【3】 Cardiac MRI Segmentation with Strong Anatomical Guarantees
具有强解剖学保证的心脏MRI分割
作者: Nathan Painchaud, Pierre-Marc Jodoin
备注:8 pages, accepted for MICCAI 2019
链接:https://arxiv.org/abs/1907.02865
【4】 Data Efficient Unsupervised Domain Adaptation for Cross-Modality Image Segmentation
用于跨模态图像分割的数据高效无监督域自适应
作者: Cheng Ouyang, Daniel Rueckert
备注:Accepted by MICCAI 2019
链接:https://arxiv.org/abs/1907.02766
【5】 Adversarial Learning with Multiscale Features and Kernel Factorization for Retinal Blood Vessel Segmentation
基于多尺度特征和核因子分解的对抗性学习在视网膜血管分割中的应用
作者: Farhan Akram, Domenec Puig
链接:https://arxiv.org/abs/1907.02742
[GAN/对抗式/生成式相关]:
【1】 Large Scale Adversarial Representation Learning
大规模对抗性表征学习
作者: Jeff Donahue, Karen Simonyan
链接:https://arxiv.org/abs/1907.02544
【2】 Generating large labeled data sets for laparoscopic image processing tasks using unpaired image-to-image translation
使用不配对的图像到图像转换为腹腔镜图像处理任务生成大型标记数据集
作者: Micha Pfeiffer, Stefanie Speidel
备注:Accepted at MICCAI 2019
链接:https://arxiv.org/abs/1907.02882
【3】 Degenerative Adversarial NeuroImage Nets: Generating Images that Mimic Disease Progression
退化对抗性神经映像网:生成模拟疾病进展的图像
作者: Daniele Ravi, Neil P. Oxtoby
备注:Paper accepted for MICCAI 2019
链接:https://arxiv.org/abs/1907.02787
【4】 Evaluating the distribution learning capabilities of GANs
评估GANS的分布式学习能力
作者: Amit Rege, Claire Monteleoni
链接:https://arxiv.org/abs/1907.02662
[迁移学习/domain/主动学习相关]:
【1】 A Survey of Pruning Methods for Efficient Person Re-identification Across Domains
用于跨域高效人员重新识别的剪枝方法综述
作者: Hugo Masson, Eric Granger
链接:https://arxiv.org/abs/1907.02547
[裁剪/量化/加速相关]:
【1】 High-throughput Onboard Hyperspectral Image Compression with Ground-based CNN Reconstruction
基于地面CNN重建的高通量星载高光谱图像压缩
作者: Diego Valsesia, Enrico Magli
链接:https://arxiv.org/abs/1907.02959
[其他]:
【1】 A Performance Evaluation of Correspondence Grouping Methods for 3D Rigid Data Matching
三维刚性数据匹配对应分组方法的性能评价
作者: Jiaqi Yang, Yanning Zhang
备注:Extension of 3DV 2017 paper
链接:https://arxiv.org/abs/1907.02890
【2】 Distilling with Residual Network for Single Image Super Resolution
基于残差网络的单幅图像超分辨率提取
作者: Xiaopeng Sun, Furui Bai
备注:6 pages; Accepted to ICME2019
链接:https://arxiv.org/abs/1907.02843
【3】 Depth Restoration: A fast low-rank matrix completion via dual-graph regularization
深度恢复:通过对偶图正则化的快速低秩矩阵完成
作者: Wenxiang Zuo, Xianming Liu
链接:https://arxiv.org/abs/1907.02841
【4】 Visual Appearance Analysis of Forest Scenes for Monocular SLAM
单目SLAM森林场景视觉外观分析
作者: James Garforth, Barbara Webb
备注:Accepted to ICRA 2019
链接:https://arxiv.org/abs/1907.02824
【5】 C^3 Framework: An Open-source PyTorch Code for Crowd Counting
C^3框架:一个用于人群计数的开源PyTorch代码
作者: Junyu Gao, Jun Wen
链接:https://arxiv.org/abs/1907.02724
【6】 Prior Activation Distribution (PAD): A Versatile Representation to Utilize DNN Hidden Units
先前激活分布(PAD):一种利用DNN隐藏单元的通用表示
作者: Lakmal Meegahapola, Archan Misra
备注:Submitted to NeurIPS 2019
链接:https://arxiv.org/abs/1907.02711
【7】 Primate Face Identification in the Wild
野外灵长类动物的面部识别
作者: Ankita Shukla, Yadvendradev Jhala
备注:arXiv admin note: text overlap with arXiv:1811.00743
链接:https://arxiv.org/abs/1907.02642
【8】 Attentive Context Normalization for Robust Permutation-Equivariant Learning
鲁棒置换-等变学习的注意上下文归一化
作者: Weiwei Sun, Kwang Moo Yi
链接:https://arxiv.org/abs/1907.02545
【9】 Visualizing Uncertainty and Saliency Maps of Deep Convolutional Neural Networks for Medical Imaging Applications
用于医学影像应用的深层卷积神经网络的不确定性和显着性图的可视化
作者: Jae Duk Seo
链接:https://arxiv.org/abs/1907.02940
【10】 Improved local search for graph edit distance
改进的图形编辑距离的本地搜索
作者: Nicolas Boria, Luc Brun
链接:https://arxiv.org/abs/1907.02929
【11】 A new method for determining the filled point of the tooth by Bit-Plane Algorithm
用位平面算法确定牙齿填充点的一种新方法
作者: Zahra Alidousti, Maryam Taghizadeh Dehkordi
备注:2019 IEEE 4th Conference on Technology In Electrical and Computer Engineering (ETECH 2019) Information and Communication Technology (ICT) Tehran, Iran
链接:https://arxiv.org/abs/1907.02873
【12】 Incremental Concept Learning via Online Generative Memory Recall
通过在线生成记忆回忆的增量概念学习
作者: Huaiyu Li, Bao-Gang Hu
链接:https://arxiv.org/abs/1907.02788
【13】 Extraction and Analysis of Fictional Character Networks: A Survey
虚拟人物网络的提取与分析综述
作者: Vincent Labatut (LIA), Xavier Bost (LIA)
链接:https://arxiv.org/abs/1907.02704
【14】 Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network
基于深层双线性卷积神经网络的盲像质评价
作者: Weixia Zhang, Zhou Wang
链接:https://arxiv.org/abs/1907.02665
【15】 Automated Non-Destructive Inspection of Fused Filament Fabrication Components Using Thermographic Signal Reconstruction
利用热成像信号重构的熔丝制造元件的自动无损检测
作者: Joshua E. Siegel, Steven M. Shepard
链接:https://arxiv.org/abs/1907.02634
【16】 Measuring the Data Efficiency of Deep Learning Methods
测量深度学习方法的数据效率
作者: Hlynur Davíð Hlynsson, Laurenz Wiskott
链接:https://arxiv.org/abs/1907.02549
翻译:腾讯翻译君