Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Miao Zheng 104429be00 | 1 year ago | |
---|---|---|
.. | ||
README.md | 1 year ago | |
danet.yml | 2 years ago | |
danet_r50-d8_512x512_20k_voc12aug.py | 3 years ago | |
danet_r50-d8_512x512_40k_voc12aug.py | 3 years ago | |
danet_r50-d8_512x512_80k_ade20k.py | 3 years ago | |
danet_r50-d8_512x512_160k_ade20k.py | 3 years ago | |
danet_r50-d8_512x1024_40k_cityscapes.py | 3 years ago | |
danet_r50-d8_512x1024_80k_cityscapes.py | 3 years ago | |
danet_r50-d8_769x769_40k_cityscapes.py | 3 years ago | |
danet_r50-d8_769x769_80k_cityscapes.py | 3 years ago | |
danet_r101-d8_512x512_20k_voc12aug.py | 3 years ago | |
danet_r101-d8_512x512_40k_voc12aug.py | 3 years ago | |
danet_r101-d8_512x512_80k_ade20k.py | 3 years ago | |
danet_r101-d8_512x512_160k_ade20k.py | 3 years ago | |
danet_r101-d8_512x1024_40k_cityscapes.py | 3 years ago | |
danet_r101-d8_512x1024_80k_cityscapes.py | 3 years ago | |
danet_r101-d8_769x769_40k_cityscapes.py | 3 years ago | |
danet_r101-d8_769x769_80k_cityscapes.py | 3 years ago |
Dual Attention Network for Scene Segmentation
In this paper, we address the scene segmentation task by capturing rich contextual dependencies based on the selfattention mechanism. Unlike previous works that capture contexts by multi-scale features fusion, we propose a Dual Attention Networks (DANet) to adaptively integrate local features with their global dependencies. Specifically, we append two types of attention modules on top of traditional dilated FCN, which model the semantic interdependencies in spatial and channel dimensions respectively. The position attention module selectively aggregates the features at each position by a weighted sum of the features at all positions. Similar features would be related to each other regardless of their distances. Meanwhile, the channel attention module selectively emphasizes interdependent channel maps by integrating associated features among all channel maps. We sum the outputs of the two attention modules to further improve feature representation which contributes to more precise segmentation results. We achieve new state-of-the-art segmentation performance on three challenging scene segmentation datasets, i.e., Cityscapes, PASCAL Context and COCO Stuff dataset. In particular, a Mean IoU score of 81.5% on Cityscapes test set is achieved without using coarse data. We make the code and trained model publicly available at this https URL.
@article{fu2018dual,
title={Dual Attention Network for Scene Segmentation},
author={Jun Fu, Jing Liu, Haijie Tian, Yong Li, Yongjun Bao, Zhiwei Fang,and Hanqing Lu},
booktitle={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2019}
}
Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
---|---|---|---|---|---|---|---|---|---|
DANet | R-50-D8 | 512x1024 | 40000 | 7.4 | 2.66 | 78.74 | - | config | model | log |
DANet | R-101-D8 | 512x1024 | 40000 | 10.9 | 1.99 | 80.52 | - | config | model | log |
DANet | R-50-D8 | 769x769 | 40000 | 8.8 | 1.56 | 78.88 | 80.62 | config | model | log |
DANet | R-101-D8 | 769x769 | 40000 | 12.8 | 1.07 | 79.88 | 81.47 | config | model | log |
DANet | R-50-D8 | 512x1024 | 80000 | - | - | 79.34 | - | config | model | log |
DANet | R-101-D8 | 512x1024 | 80000 | - | - | 80.41 | - | config | model | log |
DANet | R-50-D8 | 769x769 | 80000 | - | - | 79.27 | 80.96 | config | model | log |
DANet | R-101-D8 | 769x769 | 80000 | - | - | 80.47 | 82.02 | config | model | log |
Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
---|---|---|---|---|---|---|---|---|---|
DANet | R-50-D8 | 512x512 | 80000 | 11.5 | 21.20 | 41.66 | 42.90 | config | model | log |
DANet | R-101-D8 | 512x512 | 80000 | 15 | 14.18 | 43.64 | 45.19 | config | model | log |
DANet | R-50-D8 | 512x512 | 160000 | - | - | 42.45 | 43.25 | config | model | log |
DANet | R-101-D8 | 512x512 | 160000 | - | - | 44.17 | 45.02 | config | model | log |
Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
---|---|---|---|---|---|---|---|---|---|
DANet | R-50-D8 | 512x512 | 20000 | 6.5 | 20.94 | 74.45 | 75.69 | config | model | log |
DANet | R-101-D8 | 512x512 | 20000 | 9.9 | 13.76 | 76.02 | 77.23 | config | model | log |
DANet | R-50-D8 | 512x512 | 40000 | - | - | 76.37 | 77.29 | config | model | log |
DANet | R-101-D8 | 512x512 | 40000 | - | - | 76.51 | 77.32 | config | model | log |
No Description
Python Markdown Shell Dockerfile other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》