Skip to content

Model Zoo

Jump to bottom
Bolei Zhou edited this page Jan 15, 2017 · 5 revisions

This is the model zoo of MIT Scene Parsing Benchmark. You could find the scene parsing models trained on MIT Scene Parsing Benchmark or add your own models below.

Baseline models trained by MIT Vision Team

  • DilatedNet and FCN: The baseline models used in the arXiv paper.
  • Online Demo: Upload and test your own image for scene parsing. The demo is powered by DilatedNet.
  • Demo Code: a matlab demo code to generate scene parsing for a given image.
  • Training code: the caffe and torch code to train the DilatedNet and FCN to reproduce the resuts.

Semantic Understanding of Scenes through ADE20K Dataset.B. Zhou, H. Zhao, X. Puig, S. Fidler, A. Barriuso and A. Torralba.arXiv:1608.05442

Clone this wiki locally