Holger Caesar (s1373211)
Thu 31 Mar 2016, 12:45 - 13:45

If you have a question about this talk, please contact: Steph Smith (ssmith32)

In this talk we propose a novel method for semantic segmentation, the task of labeling each pixel in an image with a semantic class. Our method combines the advantages of the two main competing paradigms. Methods based on region classification offer proper spatial support for appearance measurements, but typically operate in two separate stages, none of which targets pixel-labeling performance at the end of the pipeline. More recent Fully Convolutional Neural Network methods are capable of end-to-end training for the final pixel labeling, but resort to fixed patches as spatial support. We show how to modify modern region-based approaches to enable end-to-end training for semantic segmentation. This is achieved via a differentiable region-to-pixel layer, and a differentiable free-form Region-of-Interest pooling layer. Our method outperforms the previous state-of-the-art in terms of class-average pixel accuracy with 64.0% on SIFT Flow and 49.9% on PASCAL Context.