By Zilong Huang, Xinggang Wang, Lichao Huang, Chang Huang, Yunchao Wei, Wenyu Liu.

This code is a implementation of the experiments on Cityscapes in the CCNet. We implement our method based on open source pytorch segmentation toolbox.

Long-range dependencies can capture useful contextual information to benefit visual understanding problems. In this work, we propose a Criss-Cross Network (CCNet) for obtaining such important information through a more effective and efficient way. Concretely, for each pixel, our CCNet can harvest the contextual information of its surrounding pixels on the criss-cross path through a novel criss-cross attention module. By taking a further recurrent operation, each pixel can finally capture the long-range dependencies from all pixels. Overall, our CCNet is with the following merits:

• GPU memory friendly
• High computational efficiency
• The state-of-the-art performance

Overview of the proposed CCNet for semantic segmentation. The proposed recurrent criss-cross attention takes as input feature maps H and output feature maps H'' which obtain rich and dense contextual information from all pixels. Recurrent criss-cross attention module can be unrolled into R=2 loops, in which all Criss-Cross Attention modules share parameters.

To get a deeper understanding of our RCCA, we visualize the learned attention masks as shown in the figure. For each input image, we select one point (green cross) and show its corresponding attention maps when R=1 and R=2 in columns 2 and 3 respectively. In the figure, only contextual information from the criss-cross path of the target point is capture when R=1. By adopting one more criss-cross module, ie, R=2 the RCCA can finally aggregate denser and richer contextual information compared with that of R=1. Besides, we observe that the attention module could capture semantic similarity and long-range dependencies.

CCNet is released under the MIT License (refer to the LICENSE file for details).

If you find CCNet useful in your research, please consider citing:

@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},
    journal = {arXiv preprint arXiv:1811.11721},
    year={2018}
}

To install PyTorch>=0.4.0, please refer to https://github.com/pytorch/pytorch#installation.
4 x 12G GPUs (e.g. TITAN XP)

Some parts of InPlace-ABN and Criss-Cross Attention have native CUDA implementations, which must be compiled with the following commands:

cd libs
sh build.sh
python build.py

cd ../cc_attention
sh build.sh
python build.py

The build.sh script assumes that the nvcc compiler is available in the current system search path. The CUDA kernels are compiled for sm_50, sm_52 and sm_61 by default. To change this (e.g. if you are using a Kepler GPU), please edit the CUDA_GENCODE variable in build.sh.

Plesae download cityscapes dataset and unzip the dataset into YOUR_CS_PATH.

Please download MIT imagenet pretrained resnet101-imagenet.pth, and put it into dataset folder.

./run_local.sh YOUR_CS_PATH

The work was mainly done during an internship at Horizon Robotics.

Self-attention related methods:
Object Context Network
Dual Attention Network
Semantic segmentation toolboxs:
pytorch-segmentation-toolbox
semantic-segmentation-pytorch
PyTorch-Encoding