Log In Sign Up

Global and Local Features through Gaussian Mixture Models on Image Semantic Segmentation

by   Darwin Saire, et al.

The semantic segmentation task aims at dense classification at the pixel-wise level. Deep models exhibited progress in tackling this task. However, one remaining problem with these approaches is the loss of spatial precision, often produced at the segmented objects' boundaries. Our proposed model addresses this problem by providing an internal structure for the feature representations while extracting a global representation that supports the former. To fit the internal structure, during training, we predict a Gaussian Mixture Model from the data, which, merged with the skip connections and the decoding stage, helps avoid wrong inductive biases. Furthermore, our results show that we can improve semantic segmentation by providing both learning representations (global and local) with a clustering behavior and combining them. Finally, we present results demonstrating our advances in Cityscapes and Synthia datasets.


page 6

page 7

page 8

page 9

page 11

page 12

page 13

page 14


Scale-Based Gaussian Coverings: Combining Intra and Inter Mixture Models in Image Segmentation

By a "covering" we mean a Gaussian mixture model fit to observed data. A...

GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models

Prevalent semantic segmentation solutions are, in essence, a dense discr...

Analyzing Learned Convnet Features with Dirichlet Process Gaussian Mixture Models

Convolutional Neural Networks (Convnets) have achieved good results in a...

Hierarchical Gaussian Mixture Model with Objects Attached to Terminal and Non-terminal Dendrogram Nodes

A hierarchical clustering algorithm based on Gaussian mixture model is p...

OrthoSeg: A Deep Multimodal Convolutional Neural Network for Semantic Segmentation of Orthoimagery

This paper addresses the task of semantic segmentation of orthoimagery u...

Boosting Semi-Supervised Semantic Segmentation with Probabilistic Representations

Recent breakthroughs in semi-supervised semantic segmentation have been ...

FuSS: Fusing Superpixels for Improved Segmentation Consistency

In this work, we propose two different approaches to improve the semanti...