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 | |
ccnet.yml | 2 years ago | |
ccnet_r50-d8_512x512_20k_voc12aug.py | 3 years ago | |
ccnet_r50-d8_512x512_40k_voc12aug.py | 3 years ago | |
ccnet_r50-d8_512x512_80k_ade20k.py | 3 years ago | |
ccnet_r50-d8_512x512_160k_ade20k.py | 3 years ago | |
ccnet_r50-d8_512x1024_40k_cityscapes.py | 3 years ago | |
ccnet_r50-d8_512x1024_80k_cityscapes.py | 3 years ago | |
ccnet_r50-d8_769x769_40k_cityscapes.py | 3 years ago | |
ccnet_r50-d8_769x769_80k_cityscapes.py | 3 years ago | |
ccnet_r101-d8_512x512_20k_voc12aug.py | 3 years ago | |
ccnet_r101-d8_512x512_40k_voc12aug.py | 3 years ago | |
ccnet_r101-d8_512x512_80k_ade20k.py | 3 years ago | |
ccnet_r101-d8_512x512_160k_ade20k.py | 3 years ago | |
ccnet_r101-d8_512x1024_40k_cityscapes.py | 3 years ago | |
ccnet_r101-d8_512x1024_80k_cityscapes.py | 3 years ago | |
ccnet_r101-d8_769x769_40k_cityscapes.py | 3 years ago | |
ccnet_r101-d8_769x769_80k_cityscapes.py | 3 years ago |
CCNet: Criss-Cross Attention for Semantic Segmentation
Contextual information is vital in visual understanding problems, such as semantic segmentation and object detection. We propose a Criss-Cross Network (CCNet) for obtaining full-image contextual information in a very effective and efficient way. Concretely, for each pixel, a novel criss-cross attention module harvests the contextual information of all the pixels on its criss-cross path. By taking a further recurrent operation, each pixel can finally capture the full-image dependencies. Besides, a category consistent loss is proposed to enforce the criss-cross attention module to produce more discriminative features. Overall, CCNet is with the following merits: 1) GPU memory friendly. Compared with the non-local block, the proposed recurrent criss-cross attention module requires 11x less GPU memory usage. 2) High computational efficiency. The recurrent criss-cross attention significantly reduces FLOPs by about 85% of the non-local block. 3) The state-of-the-art performance. We conduct extensive experiments on semantic segmentation benchmarks including Cityscapes, ADE20K, human parsing benchmark LIP, instance segmentation benchmark COCO, video segmentation benchmark CamVid. In particular, our CCNet achieves the mIoU scores of 81.9%, 45.76% and 55.47% on the Cityscapes test set, the ADE20K validation set and the LIP validation set respectively, which are the new state-of-the-art results. The source codes are available at this https URL.
@article{huang2018ccnet,
title={CCNet: Criss-Cross Attention for Semantic Segmentation},
author={Huang, Zilong and Wang, Xinggang and Huang, Lichao and Huang, Chang and Wei, Yunchao and Liu, Wenyu},
booktitle={ICCV},
year={2019}
}
Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
---|---|---|---|---|---|---|---|---|---|
CCNet | R-50-D8 | 512x1024 | 40000 | 6 | 3.32 | 77.76 | 78.87 | config | model | log |
CCNet | R-101-D8 | 512x1024 | 40000 | 9.5 | 2.31 | 76.35 | 78.19 | config | model | log |
CCNet | R-50-D8 | 769x769 | 40000 | 6.8 | 1.43 | 78.46 | 79.93 | config | model | log |
CCNet | R-101-D8 | 769x769 | 40000 | 10.7 | 1.01 | 76.94 | 78.62 | config | model | log |
CCNet | R-50-D8 | 512x1024 | 80000 | - | - | 79.03 | 80.16 | config | model | log |
CCNet | R-101-D8 | 512x1024 | 80000 | - | - | 78.87 | 79.90 | config | model | log |
CCNet | R-50-D8 | 769x769 | 80000 | - | - | 79.29 | 81.08 | config | model | log |
CCNet | R-101-D8 | 769x769 | 80000 | - | - | 79.45 | 80.66 | config | model | log |
Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
---|---|---|---|---|---|---|---|---|---|
CCNet | R-50-D8 | 512x512 | 80000 | 8.8 | 20.89 | 41.78 | 42.98 | config | model | log |
CCNet | R-101-D8 | 512x512 | 80000 | 12.2 | 14.11 | 43.97 | 45.13 | config | model | log |
CCNet | R-50-D8 | 512x512 | 160000 | - | - | 42.08 | 43.13 | config | model | log |
CCNet | R-101-D8 | 512x512 | 160000 | - | - | 43.71 | 45.04 | config | model | log |
Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
---|---|---|---|---|---|---|---|---|---|
CCNet | R-50-D8 | 512x512 | 20000 | 6 | 20.45 | 76.17 | 77.51 | config | model | log |
CCNet | R-101-D8 | 512x512 | 20000 | 9.5 | 13.64 | 77.27 | 79.02 | config | model | log |
CCNet | R-50-D8 | 512x512 | 40000 | - | - | 75.96 | 77.04 | config | model | log |
CCNet | R-101-D8 | 512x512 | 40000 | - | - | 77.87 | 78.90 | 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》