English

Location-aware Upsampling for Semantic Segmentation

Computer Vision and Pattern Recognition 2019-11-15 v2

Abstract

Many successful learning targets such as minimizing dice loss and cross-entropy loss have enabled unprecedented breakthroughs in segmentation tasks. Beyond these semantic metrics, this paper aims to introduce location supervision into semantic segmentation. Based on this idea, we present a Location-aware Upsampling (LaU) that adaptively refines the interpolating coordinates with trainable offsets. Then, location-aware losses are established by encouraging pixels to move towards well-classified locations. An LaU is offset prediction coupled with interpolation, which is trained end-to-end to generate confidence score at each position from coarse to fine. Guided by location-aware losses, the new module can replace its plain counterpart (\textit{e.g.}, bilinear upsampling) in a plug-and-play manner to further boost the leading encoder-decoder approaches. Extensive experiments validate the consistent improvement over the state-of-the-art methods on benchmark datasets. Our code is available at https://github.com/HolmesShuan/Location-aware-Upsampling-for-Semantic-Segmentation

Keywords

Cite

@article{arxiv.1911.05250,
  title  = {Location-aware Upsampling for Semantic Segmentation},
  author = {Xiangyu He and Zitao Mo and Qiang Chen and Anda Cheng and Peisong Wang and Jian Cheng},
  journal= {arXiv preprint arXiv:1911.05250},
  year   = {2019}
}
R2 v1 2026-06-23T12:13:49.587Z