今天,计算机视觉三大顶会之一CVPR2020接收结果已经公布,一共有1470篇论文被接收,接收率为22%,相比去年降低3个百分点,竞争越来越激烈。
计算机视觉顶会CVPR2020官方今日发布接收论文列表(编号):
http://cvpr2020.thecvf.com/sites/default/files/2020-02/accepted_list.txt
专知在这里整理现有开放的一些CVPR论文,抢先看!
1.GhostNet: More Features from Cheap Operations
(超越Mobilenet v3的架构)
论文链接:
https://arxiv.org/pdf/1911.11907arxiv.org
模型(在ARM CPU上的表现惊人):
https://github.com/iamhankai/ghostnetgithub.com
We beat other SOTA lightweight CNNs such as MobileNetV3 and FBNet.
2. AdderNet: Do We Really Need Multiplications in Deep Learning?
(加法神经网络)
论文链接:
https://arxiv.org/pdf/1912.13200
论文链接:
https://github.com/huawei-noah/AdderNet
3.
Frequency Domain Compact 3D Convolutional Neural Networks (3dCNN压缩)
论文链接:
https://arxiv.org/pdf/1909.04977
开源代码:
https://github.com/huawei-noah/CARSgithub.com
4.
A Semi-Supervised Assessor of Neural Architectures (神经网络精度预测器 NAS)
5.
Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection(NAS 检测)
backbone-neck-head一起搜索, 三位一体
6.
CARS: Contunuous Evolution for Efficient Neural Architecture Search (连续进化的NAS)
论文链接:
https://arxiv.org/abs/1909.04977
7.
On Positive-Unlabeled Classification in GAN (PU+GAN)
8.
Learning multiview 3D point cloud registration
(3D点云)
论文链接:
arxiv.org/abs/2001.05119
9.
Multi-Modal Domain Adaptation for Fine-Grained Action Recognition
(细粒度动作识别)
论文链接:
arxiv.org/abs/2001.09691
10.
Action Modifiers:
Learning fro
m Adverbs in Instructional Video
论文链接:
arxiv.org/abs/1912.06617
11. PolarMask: Single Shot Instance Segmentation with Polar Representation
(实例分割建模)
论文链接:
arxiv.org/abs/1909.13226
论文解读:
https://zhuanlan.zhihu.com/p/84890413
开源代码:
https://github.com/xieenze/PolarMask
12. Rethinking Performance Estimation in Neural Architecture Search
(NAS)
由于block wise neural architecture search中真正消耗时间的是performance estimation部分,本文针对 block wise的NAS找到了最优参数,速度更快,且相关度更高。
13. Distribution Aware Coordinate Representation for Human Pose Estimation(人体姿态估计)
论文链接:
arxiv.org/abs/1910.06278
Github:
https://github.com/ilovepose/DarkPose
作者团队主页:
https://ilovepose.github.io/coco/
注:
以上工作1-7来自知乎作者王云鹤的回答:
https://www.zhihu.com/question/372070853/answer/1035056133
11来自知乎作者Johnny ez的回答:
https://www.zhihu.com/question/372070853/answer/1035186479
12来自知乎作者雨宫夏一的回答:
https://www.zhihu.com/question/372070853/answer/1035234510
13来自极市开发者
专知便捷查看
便捷下载,请关注专知公众号(点击上方蓝色专知关注)
专知,专业可信的人工智能知识分发,让认知协作更快更好!欢迎注册登录专知www.zhuanzhi.ai,获取5000+AI主题干货知识资料!
欢迎微信扫一扫加入专知人工智能知识星球群,获取最新AI专业干货知识教程资料和与专家交流咨询!
点击“
阅读原文
”,了解使用
专知
,查看获取5000+AI主题知识资源