Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation
Citations Over TimeTop 1% of 2016 papers
Abstract
Recent advances in semantic image segmentation have mostly been achieved by training deep convolutional neural networks (CNNs). We show how to improve semantic segmentation through the use of contextual information, specifically, we explore 'patch-patch' context between image regions, and 'patch-background' context. For learning from the patch-patch context, we formulate Conditional Random Fields (CRFs) with CNN-based pairwise potential functions to capture semantic correlations between neighboring patches. Efficient piecewise training of the proposed deep structured model is then applied to avoid repeated expensive CRF inference for back propagation. For capturing the patch-background context, we show that a network design with traditional multi-scale image input and sliding pyramid pooling is effective for improving performance. Our experimental results set new state-of-the-art performance on a number of popular semantic segmentation datasets, including NYUDv2, PASCAL VOC 2012, PASCAL-Context, and SIFT-flow. In particular, we achieve an intersection-overunion score of 78:0 on the challenging PASCAL VOC 2012 dataset.
Related Papers
- Chinese Named Entity Recognition with Conditional Random Fields(2006)
- → Result identification for biomedical abstracts using Conditional Random Fields(2008)6 cited
- → A Recognition Approach Study on Chinese Field Term Based Mutual Information /Conditional Random Fields(2012)3 cited
- Named entity recognition in Chinese medical records based on cascaded conditional random field(2014)
- → Biomedical Named Entity Recognition Using Second-Order Conditional Random Fields(2011)