Image Segmentation Models

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.

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

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Semantic Segmentation 2 20.00%
Change Detection 1 10.00%
Autonomous Driving 1 10.00%
Image Segmentation 1 10.00%
Retrieval 1 10.00%
Text Matching 1 10.00%
Video-Text Retrieval 1 10.00%
Crowd Counting 1 10.00%
Scene Segmentation 1 10.00%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories