https://github.com/nv-tlabs/GSCNN
Gated-Shape CNN for Semantic Segmentation (ICCV 2019)
https://github.com/nv-tlabs/GSCNN
computer-vision deep-learning iccv2019 nv-tlabs pytorch semantic-boundaries semantic-segmentation
Last synced: about 1 year ago
JSON representation
Gated-Shape CNN for Semantic Segmentation (ICCV 2019)
- Host: GitHub
- URL: https://github.com/nv-tlabs/GSCNN
- Owner: nv-tlabs
- License: other
- Created: 2019-07-11T18:43:07.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2023-10-23T15:39:04.000Z (over 2 years ago)
- Last Synced: 2025-03-26T06:06:08.083Z (about 1 year ago)
- Topics: computer-vision, deep-learning, iccv2019, nv-tlabs, pytorch, semantic-boundaries, semantic-segmentation
- Language: Python
- Homepage: https://nv-tlabs.github.io/GSCNN/
- Size: 162 MB
- Stars: 920
- Watchers: 35
- Forks: 201
- Open Issues: 56
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-computer-vision-papers - 2019ICCV - tlabs.github.io/GSCNN/) (SemanticSeg)
- StarryDivineSky - nv-tlabs/GSCNN - Shape CNN for Semantic Segmentation”，旨在提升分割精度，尤其是在处理复杂形状和结构时。GSCNN的核心思想是利用门控形状CNN，通过形状信息引导分割过程。它包含两个主要分支：一个常规的分割分支和一个形状流分支。形状流分支负责学习物体的形状表示，并使用门控机制将形状信息融入到分割分支中。这种结构使得网络能够更好地理解物体的整体形状，从而提高分割的准确性和鲁棒性。项目提供了代码、预训练模型和数据集，方便研究者复现结果和进行进一步研究。GSCNN在多个数据集上取得了优秀的性能，证明了其在语义分割任务中的有效性。该项目使用PyTorch框架实现。 (对象检测_分割 / 资源传输下载)
README
# GSCNN
This is the official code for:
#### Gated-SCNN: Gated Shape CNNs for Semantic Segmentation
[Towaki Takikawa](https://tovacinni.github.io), [David Acuna](http://www.cs.toronto.edu/~davidj/), [Varun Jampani](https://varunjampani.github.io), [Sanja Fidler](http://www.cs.toronto.edu/~fidler/)
ICCV 2019
**[[Paper](https://arxiv.org/abs/1907.05740)] [[Project Page](https://nv-tlabs.github.io/GSCNN/)]**
Based on based on https://github.com/NVIDIA/semantic-segmentation.
## License
```
Copyright (C) 2019 NVIDIA Corporation. Towaki Takikawa, David Acuna, Varun Jampani, Sanja Fidler
All rights reserved.
Licensed under the CC BY-NC-SA 4.0 license (https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode).
Permission to use, copy, modify, and distribute this software and its documentation
for any non-commercial purpose is hereby granted without fee, provided that the above
copyright notice appear in all copies and that both that copyright notice and this
permission notice appear in supporting documentation, and that the name of the author
not be used in advertising or publicity pertaining to distribution of the software
without specific, written prior permission.
THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR ANY PARTICULAR PURPOSE.
IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL
DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING
OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
~
```
## Usage
##### Clone this repo
```bash
git clone https://github.com/nv-tlabs/GSCNN
cd GSCNN
```
#### Python requirements
Currently, the code supports Python 3
* numpy
* PyTorch (>=1.1.0)
* torchvision
* scipy
* scikit-image
* tensorboardX
* tqdm
* torch-encoding
* opencv
* PyYAML
#### Download pretrained models
Download the pretrained model from the [Google Drive Folder](https://drive.google.com/file/d/1wlhAXg-PfoUM-rFy2cksk43Ng3PpsK2c/view), and save it in 'checkpoints/'
#### Download inferred images
Download (if needed) the inferred images from the [Google Drive Folder](https://drive.google.com/file/d/105WYnpSagdlf5-ZlSKWkRVeq-MyKLYOV/view)
#### Evaluation (Cityscapes)
```bash
python train.py --evaluate --snapshot checkpoints/best_cityscapes_checkpoint.pth
```
#### Training
A note on training- we train on 8 NVIDIA GPUs, and as such, training will be an issue with WiderResNet38 if you try to train on a single GPU.
If you use this code, please cite:
```
@article{takikawa2019gated,
title={Gated-SCNN: Gated Shape CNNs for Semantic Segmentation},
author={Takikawa, Towaki and Acuna, David and Jampani, Varun and Fidler, Sanja},
journal={ICCV},
year={2019}
}
```