Superpixel-enhanced Pairwise Conditional Random Field for Semantic Segmentation

2018-05-29 · Li Sulimowicz, Ishfaq Ahmad, Alexander Aved

Superpixel-based Higher-order Conditional Random Fields (CRFs) are effective in enforcing long-range consistency in pixel-wise labeling problems, such as semantic segmentation. However, their major short coming is considerably longer time to learn higher-order potentials and extra hyperparameters and/or weights compared with pairwise models. This paper proposes a superpixel-enhanced pairwise CRF framework that consists of the conventional pairwise as well as our proposed superpixel-enhanced pairwise (SP-Pairwise) potentials. SP-Pairwise potentials incorporate the superpixel-based higher-order cues by conditioning on a segment filtered image and share the same set of parameters as the conventional pairwise potentials. Therefore, the proposed superpixel-enhanced pairwise CRF has a lower time complexity in parameter learning and at the same time it outperforms higher-order CRF in terms of inference accuracy. Moreover, the new scheme takes advantage of the pre-trained pairwise models by reusing their parameters and/or weights, which provides a significant accuracy boost on the basis of CRF-RNN even without training. Experiments on MSRC-21 and PASCAL VOC 2012 dataset confirm the effectiveness of our method.

📄 PDF Abstract BibTeX arXiv:1805.11737

Code (1)

liyin2015/superpixel_crfasrnn tf

Tasks

Semantic Segmentation

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

CRF-RNN CRF-RNN is a formulation of a CRF as a Recurrent Neural Network. Specifically it formulates mean-field approximate inference for the…

CRF Conditional Random Fields or CRFs are a type of probabilistic graph model that take neighboring sample context into account for tasks like classification. Prediction is…

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

2018-04-05 · Li Sulimowicz, Ishfaq Ahmad, Alexander Aved

Superpixel-based Higher-order Conditional random fields (SP-HO-CRFs) are known for their effectiveness in enforcing both short and long spatial contiguity for pixelwise labelling in computer vision. However, their higher…

Image Segmentation Semantic Segmentation

Context Propagation from Proposals for Semantic Video Object Segmentation

2024-07-08 · Tinghuai Wang

In this paper, we propose a novel approach to learning semantic contextual relationships in videos for semantic object segmentation. Our algorithm derives the semantic contexts from video object proposals which encode th…

Object Segmentation Semantic Segmentation Superpixels+2

Efficient Graph Cut Optimization for Full CRFs with Quantized Edges

2018-09-13 · Olga Veksler

Fully connected pairwise Conditional Random Fields (Full-CRF) with Gaussian edge weights can achieve superior results compared to sparsely connected CRFs. However, traditional methods for Full-CRFs are too expensive. Pre…

Semantic Segmentation Superpixels

Face Parsing via a Fully-Convolutional Continuous CRF Neural Network

2017-08-12 · Lei Zhou, Zhi Liu, Xiangjian He

In this work, we address the face parsing task with a Fully-Convolutional continuous CRF Neural Network (FC-CNN) architecture. In contrast to previous face parsing methods that apply region-based subnetwork hundreds of t…

Face Parsing

Unstructured Road Segmentation using Hypercolumn based Random Forests of Local experts

2022-07-23 · Prassanna Ganesh Ravishankar, Antonio M. Lopez, Gemma M. Sanchez

Monocular vision based road detection methods are mostly based on machine learning methods, relying on classification and feature extraction accuracy, and suffer from appearance, illumination and weather changes. Traditi…

Road Segmentation Superpixels