arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1504.01013cs.CV
收藏

用于语义分割的深度结构化模型的高效分段训练

Efficient piecewise training of deep structured models for semantic segmentation

The University of Adelaide(阿德莱德大学);Australian Centre for Robotic Vision(澳大利亚机器人视觉中心)

Guosheng Lin, Chunhua Shen, Anton van dan Hengel, Ian Reid

摘要:

语义图像分割的最新进展主要是通过训练深度卷积神经网络(CNN)实现的。我们将展示如何通过使用上下文信息来提高语义分割;具体而言,我们将探索图像区域之间的“补丁-补丁”上下文和“补丁-背景”上下文。为了从补丁补丁上下文中学习,我们用基于CNN的成对势函数来构造条件随机场(CRF),以捕获相邻补丁之间的语义相关性。然后应用所提出的深度结构化模型的有效分段训练,以避免用于反向传播的重复昂贵的CRF推断。对于捕获补丁背景上下文,我们表明,传统的多尺度图像输入和滑动金字塔池的网络设计是有效的,以提高性能。我们的实验结果在一些流行的语义分割数据集上设置了新的最先进的性能,包括NYUDv 2,PASCAL VOC 2012,PASCAL上下文和SIFT流。特别是,我们在具有挑战性的PASCAL VOC 2012数据集上实现了78.0的交叉-联合得分。

英文摘要:

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-over-union score of 78.0 on the challenging PASCAL VOC 2012 dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑