Cars Can't Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networks

CVPR 2020  ·  Sungha Choi, Joanne T. Kim, Jaegul Choo ·

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 ResNet-101 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 at https://github.com/shachoi/HANet

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract

Datasets


Results from the Paper


Ranked #17 on Semantic Segmentation on Cityscapes test (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Semantic Segmentation Cityscapes test HANet (Height-driven Attention Networks by LGE A&B)(coarse) Mean IoU (class) 83.2% # 17

Methods