Fast Semantic Image Segmentation with High Order Context and Guided Filtering

Abstract

This paper describes a fast and accurate semantic image segmentation approach that encodes not only the discriminative features from deep neural networks, but also the high-order context compatibility among adjacent objects as well as low level image features. We formulate the underlying problem as the conditional random field that embeds local feature extraction, clique potential construction, and guided filtering within the same framework, and provide an efficient coarse-to-fine solver. At the coarse level, we combine local feature representation and context interaction using a deep convolutional network, and directly learn the interaction from high order cliques with a message passing routine, avoiding time-consuming explicit graph inference for joint probability distribution. At the fine level, we introduce a guided filtering interpretation for the mean field algorithm, and achieve accurate object boundaries with 100+ faster than classic learning methods. The two parts are connected and jointly trained in an end-to-end fashion. Experimental results on Pascal VOC 2012 dataset have shown that the proposed algorithm outperforms the state-of-the-art, and that it achieves the rank 1 performance at the time of submission, both of which prove the effectiveness of this unified framework for semantic image segmentation.

arXiv comment14 pages

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Conditional Random Fields as Recurrent Neural Networks
• Fully Convolutional Networks for Semantic Segmentation
• Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
• Deep Image: Scaling up Image Recognition
• Semantic Image Segmentation via Deep Parsing Network
• Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform
• Fast Guided Filter

Cited by in corpus (2)

• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Learning Multi-level Region Consistency with Dense Multi-label Networks for Semantic Segmentation