In this work we address the task of semantic image segmentation with Deep Learning and
make three main contributions that are experimentally shown to have substantial practical
merit. First, we highlight convolution with upsampled filters, oratrous convolution', as a
powerful tool in dense prediction tasks. Atrous convolution allows us to explicitly control the
resolution at which feature responses are computed within Deep Convolutional Neural
Networks. It also allows us to effectively enlarge the field of view of filters to incorporate …

Deep Convolutional Neural Networks (DCNNs) have recently shown state of the art
performance in high level vision tasks, such as image classification and object detection.
This work brings together methods from DCNNs and probabilistic graphical models for
addressing the task of pixel-level classification (also called" semantic image segmentation").
We show that responses at the final layer of DCNNs are not sufficiently localized for accurate
object segmentation. This is due to the very invariance properties that make DCNNs good …