CV Code | 计算机视觉开源周报 20190701期

我爱计算机视觉 标星，更快获取CVML新技术

7月第一周的周末，盘点了这一周的新出开源代码。

神经架构搜索（小米）

FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search

Xiangxiang Chu, Bo Zhang, Ruijun Xu, Jixiang Li

https://arxiv.org/abs/1907.01845v1

http://github.com/fairnas/FairNAS

绘图的对称性检测与分类（这个蛮有意思的）

Symmetry Detection and Classification in Drawings of Graphs

Felice De Luca, Md Iqbal Hossain, Stephen Kobourov

https://arxiv.org/abs/1907.01004v1

https://github.com/enggiqbal/mlsymmetric

通过伪彩色乳房X线图片和Mask R-CNN进行全自动计算机辅助乳房块状物检测和分割

Fully automatic computer-aided mass detection and segmentation via pseudo-color mammograms and Mask R-CNN

Hang Min, Devin Wilson, Yinhuang Huang, Samuel Kelly, Stuart Crozier, Andrew P Bradley, Shekhar S. Chandra

https://arxiv.org/abs/1906.12118v1

https://github.com/Holliemin9090/Mammographic-mass-CAD-via-pseudo-color-mammogram-and-Mask-R-CNN

Avoiding Implementation Pitfalls of "Matrix Capsules with EM Routing" by Hinton et al

Ashley Daniel Gritzman

https://arxiv.org/abs/1907.00652v1

https://github.com/IBM/matrix-capsules-with-em-routing

单路径移动AutoML：高效卷积网络设计与神经架构搜索超参数优化

Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimization

Dimitrios Stamoulis, Ruizhou Ding, Di Wang, Dimitrios Lymberopoulos, Bodhi Priyantha, Jie Liu, Diana Marculescu

https://arxiv.org/abs/1907.00959v1

https://github.com/dstamoulis/single-path-nas

用于乳头状粘液性肿瘤（IPMN）诊断的膨胀神经网络

INN: Inflated Neural Networks for IPMN Diagnosis

Rodney LaLonde, Irene Tanner, Katerina Nikiforaki, Georgios Z. Papadakis, Pujan Kandel, Candice W. Bolan, Michael B. Wallace, Ulas Bagci

https://arxiv.org/abs/1907.00437v1

https://github.com/lalonderodney/INN-Inflated-Neural-Nets

1D卷积神经网络用于树叶与时序信号分类

A 1d convolutional network for leaf and time series classification

Dongyang Kuang

https://arxiv.org/abs/1907.00069v1

https://github.com/dykuang/Leaf

实时RGB-D图像的深度校正

Spatio-thermal depth correction of RGB-D sensors based on Gaussian Processes in real-time

Christoph Heindl, Thomas Pönitz, Gernot Stübl, Andreas Pichler, Josef Scharinger

https://arxiv.org/abs/1907.00549v1

https://github.com/cheind/rgbd-correction

医学图像分割 | 三维经直肠超声前列腺分割的深层注意特征

Deep Attentive Features for Prostate Segmentation in 3D Transrectal Ultrasound

Yi Wang, Haoran Dou, Xiaowei Hu, Lei Zhu, Xin Yang, Ming Xu, Jing Qin, Pheng-Ann Heng, Tianfu Wang, Dong Ni

https://arxiv.org/abs/1907.01743v1

https://github.com/wulalago/DAF3D

移动GPUs的神经网络推断，代码已经并入TensorFlow Lite

On-Device Neural Net Inference with Mobile GPUs

Juhyun Lee, Nikolay Chirkov, Ekaterina Ignasheva, Yury Pisarchyk, Mogan Shieh, Fabio Riccardi, Raman Sarokin, Andrei Kulik, Matthias Grundmann

https://arxiv.org/abs/1907.01989v1

https://tensorflow.org/lite

Mask嵌入条件GAN，用于指导高分辨率图像的生成

Mask Embedding in conditional GAN for Guided Synthesis of High Resolution Images

Yinhao Ren, Zhe Zhu, Yingzhou Li, Joseph Lo

https://arxiv.org/abs/1907.01710v1

https://github.com/johnryh/Face_Embedding_GAN

医学图像分割 | 用于MR图像的解剖和异常分割的卷积深度神经网络

DeepMRSeg: A convolutional deep neural network for anatomy and abnormality segmentation on MR images

Jimit Doshi, Guray Erus, Mohamad Habes, Christos Davatzikos

https://arxiv.org/abs/1907.02110v1

https://ipp.cbica.upenn.edu/

视线跟踪

Believe It or Not, We Know What You Are Looking at!

Dongze Lian, Zehao Yu, Shenghua Gao

https://arxiv.org/abs/1907.02364v1

https://github.com/svip-lab/GazeFollowing

更多CV开源周报：

CV Code | 计算机视觉开源周报 20190604期

CV Code | 计算机视觉开源周报 20190603期

CV Code | 计算机视觉开源周报 20190602期

CV Code | 计算机视觉开源周报 20190601期

CV专业交流群

52CV已经建立多个CV专业交流群，包括：目标检测、语义分割、姿态估计、人脸识别、医学影像处理、超分辨率、神经架构搜索、GAN、强化学习等，扫码添加CV君拉你入群，

（ 请务必注明相关方向，比如：人脸识别 ）

喜欢在QQ交流的童鞋，可以加52CV官方 QQ群 ： 702781905 。

（不会时时在线，如果没能及时通过验证还请见谅）

长按关注 我爱计算机视觉