Combining the Best of Graphical Models and ConvNets for Semantic Segmentation

Michael Cogswell, Xiao Lin, Senthil Purushwalkam, Dhruv Batra

Published 2014-12-14Version 1

We present a two-module approach to semantic segmentation that incorporates Convolutional Networks (CNNs) and Graphical Models. Graphical models are used to generate a small (5-30) set of diverse segmentations proposals, such that this set has high recall. Since the number of required proposals is so low, we can extract fairly complex features to rank them. Our complex feature of choice is a novel CNN called SegNet, which directly outputs a (coarse) semantic segmentation. Importantly, SegNet is specifically trained to optimize the corpus-level PASCAL IOU loss function. To the best of our knowledge, this is the first CNN specifically designed for semantic segmentation. This two-module approach establishes a new state of art on the PASCAL 2012 segmentation challenge, achieving 52.5%.