点击我爱计算机视觉标星，更快获取CVML新技术

计算机视觉技术发展迅速，很多时候，可悲的不是我们没有努力，而是没有跟上时代的步伐。努力coding终于出来结果了，却发现早就有人开源了，效果还比自己写的好！

CV君汇总了最近过去的一周新出的开源代码，有好几篇和网络架构搜索、训练、特征学习相关，这些基础的工作一旦有突破将会极大改进整个行业的面貌。希望对你有启发。

医学影像分割，全脑分割

3D Whole Brain Segmentation using Spatially Localized Atlas Network Tiles

Yuankai Huo, Zhoubing Xu, Yunxi Xiong, Katherine Aboud, Prasanna Parvathaneni, Shunxing Bao, Camilo Bermudez, Susan M. Resnick, Laurie E. Cutting, Bennett A. Landman

https://github.com/MASILab/SLANTbrainSeg

神经网络架构搜索

Network Slimming by Slimmable Networks: Towards One-Shot Architecture Search for Channel Numbers

Jiahui Yu, Thomas Huang

https://github.com/JiahuiYu/slimmable_networks

人体姿态迁移

Dense Intrinsic Appearance Flow for Human Pose Transfer

Yining Li, Chen Huang, Chen Change Loy

http://mmlab.ie.cuhk.edu.hk/projects/pose-transfer

自监督学习

Self-Supervised Learning via Conditional Motion Propagation

Xiaohang Zhan, Xingang Pan, Ziwei Liu, Dahua Lin, Chen Change Loy

http://mmlab.ie.cuhk.edu.hk/projects/CMP/

神经网络架构搜索

AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search

Linnan Wang, Yiyang Zhao, Yuu Jinnai, Yuandong Tian, Rodrigo Fonseca

https://github.com/linnanwang/AlphaX-NASBench101

迁移学习

Manifold Criterion Guided Transfer Learning via Intermediate Domain Generation

Lei Zhang, Shanshan Wang, Guang-Bin Huang, Wangmeng Zuo, Jian Yang, David Zhang

https://github.com/wangshanshanCQU/MCTL

特征学习

Scale-Adaptive Neural Dense Features: Learning via Hierarchical Context Aggregation

Jaime Spencer, Richard Bowden, Simon Hadfield

https://github.com/jspenmar/SAND_features

目标计数

CODA: Counting Objects via Scale-aware Adversarial Density Adaption

Li Wang, Yongbo Li, Xiangyang Xue

https://github.com/Willy0919/CODA

网络训练，权重标准化

Weight Standardization

Siyuan Qiao, Huiyu Wang, Chenxi Liu, Wei Shen, Alan Yuille

https://github.com/joe-siyuan-qiao/WeightStandardization

逼真风格迁移，基于小波变换

Photorealistic Style Transfer via Wavelet Transforms

Jaejun Yoo, Youngjung Uh, Sanghyuk Chun, Byeongkyu Kang, Jung-Woo Ha

https://github.com/ClovaAI/WCT2

基于反馈网络的图像超分辨率

Feedback Network for Image Super-Resolution

Zhen Li, Jinglei Yang, Zheng Liu, Xiaomin Yang, Gwanggil Jeon, Wei Wu

https://github.com/Paper99/SRFBN_CVPR19

支持CV君，请文末点个“在看”，谢谢～

加群交流

关注计算机视觉与机器学习技术，欢迎加入52CV群，扫码添加52CV君拉你入群，

（请务必注明:52CV）

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

麻烦给我一个“在看”！