preprintarXiv (Cornell University)Dec 22, 2014GREEN OA

Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

Institut national de recherche en informatique et en automatique · CentraleSupélec · +2 more institutions

Indexed inarxivdatacite

Abstract

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 for high level tasks. We overcome this poor localization property of deep networks by combining the responses at the final DCNN layer with a fully connected Conditional Random Field…

No related works found for this paper.