DeepAI AI Chat
Log In Sign Up

CRF Learning with CNN Features for Image Segmentation

by   Fayao Liu, et al.

Conditional Random Rields (CRF) have been widely applied in image segmentations. While most studies rely on hand-crafted features, we here propose to exploit a pre-trained large convolutional neural network (CNN) to generate deep features for CRF learning. The deep CNN is trained on the ImageNet dataset and transferred to image segmentations here for constructing potentials of superpixels. Then the CRF parameters are learnt using a structured support vector machine (SSVM). To fully exploit context information in inference, we construct spatially related co-occurrence pairwise potentials and incorporate them into the energy function. This prefers labelling of object pairs that frequently co-occur in a certain spatial layout and at the same time avoids implausible labellings during the inference. Extensive experiments on binary and multi-class segmentation benchmarks demonstrate the promise of the proposed method. We thus provide new baselines for the segmentation performance on the Weizmann horse, Graz-02, MSRC-21, Stanford Background and PASCAL VOC 2011 datasets.


page 9

page 10

page 11


Complex Relations in a Deep Structured Prediction Model for Fine Image Segmentation

Many deep learning architectures for semantic segmentation involve a Ful...

Structured Learning of Tree Potentials in CRF for Image Segmentation

We propose a new approach to image segmentation, which exploits the adva...

Learning Arbitrary Pairwise Potentials in CRFs for Semantic Segmentation

Are we using the right potential functions in the Conditional Random Fie...

Conditional Random Field and Deep Feature Learning for Hyperspectral Image Segmentation

Image segmentation is considered to be one of the critical tasks in hype...

A Multi-Layer Approach to Superpixel-based Higher-order Conditional Random Field for Semantic Image Segmentation

Superpixel-based Higher-order Conditional random fields (SP-HO-CRFs) are...

End-to-End Training of Hybrid CNN-CRF Models for Stereo

We propose a novel and principled hybrid CNN+CRF model for stereo estima...

Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs

In this work we propose a structured prediction technique that combines ...