DeepAI
Log In Sign Up

FuSS: Fusing Superpixels for Improved Segmentation Consistency

06/06/2022
by   Ian Nunes, et al.
1

In this work, we propose two different approaches to improve the semantic consistency of Open Set Semantic Segmentation. First, we propose a method called OpenGMM that extends the OpenPCS framework using a Gaussian Mixture of Models to model the distribution of pixels for each class in a multimodal manner. The second approach is a post-processing which uses superpixels to enforce highly homogeneous regions to behave equally, rectifying erroneous classified pixels within these regions, we also proposed a novel superpixel method called FuSS. All tests were performed on ISPRS Vaihingen and Potsdam datasets, and both methods were capable to improve quantitative and qualitative results for both datasets. Besides that, the post-process with FuSS achieved state-of-the-art results for both datasets. The official implementation is available at: <https://github.com/iannunes/FuSS>.

READ FULL TEXT

page 2

page 5

page 6

page 7

page 12

page 13

page 18

page 20

03/02/2022

Conditional Reconstruction for Open-set Semantic Segmentation

Open set segmentation is a relatively new and unexploredtask, with just ...
05/17/2022

Region-Aware Metric Learning for Open World Semantic Segmentation via Meta-Channel Aggregation

As one of the most challenging and practical segmentation tasks, open-wo...
11/28/2016

The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation

State-of-the-art approaches for semantic image segmentation are built on...
03/21/2022

Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation

Sparsely annotated semantic segmentation (SASS) aims to train a segmenta...
01/19/2017

PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications

PixelCNNs are a recently proposed class of powerful generative models wi...
10/05/2022

GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models

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