Methods › Computer Vision › Image Segmentation Models › HANet
Height-driven Attention Network
HANet
Introduced by Sungha Choi et al. in Cars Can't Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networks
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Height-driven Attention Network, or HANet, is a general add-on module 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.
Papers archive 2025-07-28
5 shown of 5, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
HANet: A Hierarchical Attention Network for Change Detection With Bitemporal Very-High-Resolution Remote Sensing Images 14 Apr 2024 · 1 repository · arXiv:2404.09178
-
Semantic Segmentation for Urban-Scene Images 20 Oct 2021 · 1 repository · arXiv:2110.13813
-
HANet: Hierarchical Alignment Networks for Video-Text Retrieval 26 Jul 2021 · 1 repository · arXiv:2107.12059
-
Hybrid attention network based on progressive embedding scale-context for crowd counting 4 Jun 2021 · 0 repositories · arXiv:2106.02324
-
Cars Can't Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networks 11 Mar 2020 · 1 repository · arXiv:2003.05128
Tasks archive 2025-07-28
13 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections