Cars Can’t Fly Up in the Sky: Improving Urban-Scene Segmentation via Height-Driven Attention Networks
Year: 2020
Type: conference-paper
Abstract: This paper exploits the intrinsic features of urban-scene images and proposes a general add-on module, called height-driven attention networks (HANet), for improving semantic segmentation for urban-scene images. It emphasizes informative features or classes selectively according to the vertical position of a pixel. The pixel-wise class distributions are significantly different from each other among horizontally segmented sections in the urban-scene images. Likewise, urban-scene images have their own distinct characteristics, but most semantic segmentation networks do not reflect such unique attributes in the architecture. The proposed network architecture incorporates the capability exploiting the attributes to handle the urban scene dataset effectively. We validate the consistent performance (mIoU) increase of various semantic segmentation models on two datasets when HANet is adopted. This extensive quantitative analysis demonstrates that adding our module to existing models is easy and cost-effective. Our method achieves a new state-of-the-art performance on the Cityscapes benchmark with a large margin among ResNet101 based segmentation models. Also, we show that the proposed model is coherent with the facts observed in the urban scene by visualizing and interpreting the attention map. Our code and trained models are publicly available.
Authors: Sungha Choi, Joanne T. Kim, Jaegul Choo
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Keywords: attention maps, cityscape, ResNet-101
Open Access status: green
Funders: National Research Foundation, Ministry of Science, ICT and Future Planning, National Research Foundation of Korea, Korea Advanced Institute of Science and Technology, Ministry of Science and ICT, South Korea, Institute for Information and Communications Technology Promotion, National Supercomputing Center, Korea Institute of Science and Technology Information
OpenAlex ID: W3011765439
