本周新出计算机视觉开源代码汇总（语义分割、目标检测、超分辨率、网络结构设计、训练策略等）

CV君汇总了过去一周计算机视觉领域新出的开源代码，涉及到图像增广、医学图像分割、图像恢复、目标检测、语义分割、超分辨率、显著目标检测、轻量级网络结构设计、网络规范化、标注工具等，其中有多篇来自CVPR 2019与ICML 2019的论文代码。

希望对你有帮助～

ICML 2019

mixup图像增广，噪声标签建模改进网络训练

Unsupervised label noise modeling and loss correction

Eric Arazo, Diego Ortego, Paul Albert, Noel E. O’Connor, Kevin McGuinness

https://arxiv.org/abs/1904.11238v1

https://github.com/PaulAlbert31/LabelNoiseCorrection

医学图像分割，用于脑核磁图像分割的无监督深度学习

Unsupervised deep learning for Bayesian brain MRI segmentation

Adrian V. Dalca, Evan Yu, Polina Golland, Bruce Fischl, Mert R. Sabuncu, Juan Eugenio Iglesias

https://arxiv.org/abs/1904.11319v1

http://voxelmorph.mit.edu/

ICML 2019

反锯齿模块改进网络的平移不变性

Making Convolutional Networks Shift-Invariant Again

Richard Zhang

https://arxiv.org/abs/1904.11486v1

https://richzhang.github.io/antialiased-cnns/

轻量级网络设计，全局上下文网络超越NLNet与SENet

GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond

Yue Cao, Jiarui Xu, Stephen Lin, Fangyun Wei, Han Hu

https://arxiv.org/abs/1904.11492v1

https://github.com/xvjiarui/GCNet

使用深度学习构建用于稀疏表示学习分类的新方法，超越目前state-of-the-art

IEEE Signal Processing Letters, 2019

Deep Sparse Representation-based Classification

Mahdi Abavisani, Vishal M. Patel

https://arxiv.org/abs/1904.11093v1

http://github.com/mahdiabavisani/DSRC

使用目标中心点进行目标检测、3D检测、姿态估计，Github超870颗星

Objects as Points

Xingyi Zhou, Dequan Wang, Philipp Krähenbühl

https://arxiv.org/abs/1904.07850v2

https://github.com/xingyizhou/CenterNet

整全观大规模视频理解数据集与示例代码

Holistic Large Scale Video Understanding

Ali Diba, Mohsen Fayyaz, Vivek Sharma, Manohar Paluri, Jurgen Gall, Rainer Stiefelhagen, Luc Van Gool

https://arxiv.org/abs/1904.11451v1

https://www.esat.kuleuven.be/

CVPR 2019

语义分割域适应

Bidirectional Learning for Domain Adaptation of Semantic Segmentation

Yunsheng Li, Lu Yuan, Nuno Vasconcelos

https://arxiv.org/abs/1904.10620v1

https://github.com/liyunsheng13/BDL

语义分割的预测学习

Segmenting the Future

Hsu-kuang Chiu, Ehsan Adeli, Juan Carlos Niebles

https://arxiv.org/abs/1904.10666v1

https://github.com/eddyhkchiu/segmenting_the_future/

人体形状估计

Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformation

Hao Zhu, Xinxin Zuo, Sen Wang, Xun Cao, Ruigang Yang

https://arxiv.org/abs/1904.10506v1

https://github.com/zhuhao-nju/hmd.git

用于真实图像超分辨率的多尺度深度学习

Multi-scale deep neural networks for real image super-resolution

Shangqi Gao, Xiahai Zhuang

https://arxiv.org/abs/1904.10698v1

https://github.com/shangqigao/gsq-image-SR

VGG 图像标注软件，支持目标检测语义分割的标注

The VGG Image Annotator (VIA)

Abhishek Dutta, Andrew Zisserman

https://arxiv.org/abs/1904.10699v1

http://www.robots.ox.ac.uk/~vgg/software/via/

用于高效视觉引导的机器人重排列规划的蒙特卡洛树搜索

Monte-Carlo Tree Search for Efficient Visually Guided Rearrangement Planning

Sergey Zagoruyko, Yann Labbé, Igor Kalevatykh, Ivan Laptev, Justin Carpentier, Mathieu Aubry, Josef Sivic

https://arxiv.org/abs/1904.10348v1

https://github.com/ylabbe/rearrangement-planning

学习网络路径搜索用于图像恢复，出自商汤

Path-Restore: Learning Network Path Selection for Image Restoration

Ke Yu, Xintao Wang, Chao Dong, Xiaoou Tang, Chen Change Loy

https://arxiv.org/abs/1904.10343v1

https://yuke93.github.io/Path-Restore/

使用脑电波数据与深度残差网络监控睡眠

End-to-end Sleep Staging with Raw Single Channel EEG using Deep Residual ConvNets

Ahmed Imtiaz Humayun, Asif Shahriyar Sushmit, Taufiq Hasan, Mohammed Imamul Hassan Bhuiyan

https://arxiv.org/abs/1904.10255v1

https://github.com/mHealthBuet/ASSC

神经架构搜索，网络压缩

Towards Learning of Filter-Level Heterogeneous Compression of Convolutional Neural Networks

Yochai Zur, Chaim Baskin, Evgenii Zheltonozhskii, Brian Chmiel, Itay Evron, Alex M. Bronstein

https://arxiv.org/abs/1904.09872v1

https://github.com/yochaiz/Slimmable

https://github.com/yochaiz/darts-UNIQ

自动时域一致性的视频彩色化

Automatic Temporally Coherent Video Colorization

Harrish Thasarathan, Kamyar Nazeri, Mehran Ebrahimi

https://arxiv.org/abs/1904.09527v1

https://github.com/Harry-Thasarathan/TCVC

CVPR 2019

简单的池化设计用于实时显著目标检测

A Simple Pooling-Based Design for Real-Time Salient Object Detection

Jiang-Jiang Liu, Qibin Hou, Ming-Ming Cheng, Jiashi Feng, Jianmin Jiang

https://arxiv.org/abs/1904.09569v1

 

几何感知的非监督图像翻译

TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation

Wayne Wu, Kaidi Cao, Cheng Li, Chen Qian, Chen Change Loy

https://arxiv.org/abs/1904.09571v1

https://wywu.github.io/projects/TGaGa/TGaGa.html

网络Normalization新方法，出自商汤

Switchable Whitening for Deep Representation Learning

Xingang Pan, Xiaohang Zhan, Jianping Shi, Xiaoou Tang, Ping Luo

https://arxiv.org/abs/1904.09739v1

（将要开源，还未公布地址）

显著目标检测综述

Salient Object Detection in the Deep Learning Era: An In-Depth Survey

Wenguan Wang, Qiuxia Lai, Huazhu Fu, Jianbing Shen, Haibin Ling

https://arxiv.org/abs/1904.09146v1

https://github.com/wenguanwang/SODsurvey

MIDL 2019

医学图像分割，肺部分割

XLSor: A Robust and Accurate Lung Segmentor on Chest X-Rays Using Criss-Cross Attention and Customized Radiorealistic Abnormalities Generation

Youbao Tang, Yuxing Tang, Jing Xiao, Ronald M. Summers

https://arxiv.org/abs/1904.09229v1

https://github.com/rsummers11/CADLab/tree/master/Lung_Segmentation_XLSor

CVPR 2019 workshops on explainable AI

深度神经决策森林的决策处理可视化

Visualizing the decision-making process in deep neural decision forest

Shichao Li, Kwang-Ting Cheng

https://arxiv.org/abs/1904.09201v1

https://github.com/Nicholasli1995/VisualizingNDF

LATTE： 用于LiDAR点云的开源标注工具

LATTE: Accelerating LiDAR Point Cloud Annotation via Sensor Fusion, One-Click Annotation, and Tracking

Bernie Wang, Virginia Wu, Bichen Wu, Kurt Keutzer

https://arxiv.org/abs/1904.09085v1

https://github.com/bernwang/latte

使用深度学习进行服装设计，好有趣的方向。

Fashion++: Minimal Edits for Outfit Improvement

Wei-Lin Hsiao, Isay Katsman, Chao-Yuan Wu, Devi Parikh, Kristen Grauman

https://arxiv.org/abs/1904.09261v1

http://vision.cs.utexas.edu/projects/FashionPlus