Semantic Correlation Promoted Shape-Variant Context for Segmentation

09/05/2019
by   Henghui Ding, et al.
5

Context is essential for semantic segmentation. Due to the diverse shapes of objects and their complex layout in various scene images, the spatial scales and shapes of contexts for different objects have very large variation. It is thus ineffective or inefficient to aggregate various context information from a predefined fixed region. In this work, we propose to generate a scale- and shape-variant semantic mask for each pixel to confine its contextual region. To this end, we first propose a novel paired convolution to infer the semantic correlation of the pair and based on that to generate a shape mask. Using the inferred spatial scope of the contextual region, we propose a shape-variant convolution, of which the receptive field is controlled by the shape mask that varies with the appearance of input. In this way, the proposed network aggregates the context information of a pixel from its semantic-correlated region instead of a predefined fixed region. Furthermore, this work also proposes a labeling denoising model to reduce wrong predictions caused by the noisy low-level features. Without bells and whistles, the proposed segmentation network achieves new state-of-the-arts consistently on the six public segmentation datasets.

READ FULL TEXT

page 2

page 3

page 4

page 5

page 6

page 7

page 9

page 10

research
06/08/2021

SpaceMeshLab: Spatial Context Memoization and Meshgrid Atrous Convolution Consensus for Semantic Segmentation

Semantic segmentation networks adopt transfer learning from image classi...
research
07/26/2016

Region-based semantic segmentation with end-to-end training

We propose a novel method for semantic segmentation, the task of labelin...
research
04/05/2021

Hierarchical Pyramid Representations for Semantic Segmentation

Understanding the context of complex and cluttered scenes is a challengi...
research
08/31/2019

Boundary-Aware Feature Propagation for Scene Segmentation

In this work, we address the challenging issue of scene segmentation. To...
research
08/09/2021

Complementary Patch for Weakly Supervised Semantic Segmentation

Weakly Supervised Semantic Segmentation (WSSS) based on image-level labe...
research
02/02/2020

3D Shape Segmentation with Geometric Deep Learning

The semantic segmentation of 3D shapes with a high-density of vertices c...
research
06/22/2021

The Neurally-Guided Shape Parser: A Monte Carlo Method for Hierarchical Labeling of Over-segmented 3D Shapes

Many learning-based 3D shape semantic segmentation methods assign labels...

Please sign up or login with your details

Forgot password? Click here to reset