Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
You can not select more than 25 topics
Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
nathanielbee
adbdd5f44f
|
1 year ago | |
|---|---|---|
| classification | 3 years ago | |
| segmentation | 3 years ago | |
| .gitignore | 3 years ago | |
| LICENSE.txt | 4 years ago | |
| README.md | 3 years ago | |
| train_url.txt | 1 year ago | |
README.md
Look-into-Object: Self-supervised Structure Modeling for Object Recognition
By Mohan Zhou, Yalong Bai, Wei Zhang, Tiejun Zhao, and Tao Mei.
Introduction
This project is a LIO pytorch implementation of Look-into-Object: Self-supervised Structure Modeling for Object Recognition, CVPR 2020.
Getting Started
Implementations for image classification can be found in classification/.
Implementations for image detection and segmentation can be found in segmentation/.
License
This project is released under the Apache 2.0 license.
Citation
If you use this codebase in your research, please cite our paper:
@InProceedings{Zhou_2020_CVPR,
author = {Zhou, Mohan and Bai, Yalong and Zhang, Wei and Zhao, Tiejun and Mei, Tao},
title = {Look-Into-Object: Self-Supervised Structure Modeling for Object Recognition},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}
该项目开源了一个基于图像中物体结构信息深度理解的图像识别、检测、分割算法框架。通过同一类别图像之间的共现信息首先基于弱监督的方式获得图像中物体的整体轮廓，然后基于自监督学习的方式，利用极坐标回归的损失函数来迫使神经网络对于目标物体的内部几何结构进行建模，从而辅助图像分类、检测以及分割任务来提升性能。
Jupyter Notebook Python Cuda Markdown C++ other
