Class-level Multiple Distributions Representation are Necessary for Semantic Segmentation

03/14/2023
by   Jianjian Yin, et al.
0

Existing approaches focus on using class-level features to improve semantic segmentation performance. How to characterize the relationships of intra-class pixels and inter-class pixels is the key to extract the discriminative representative class-level features. In this paper, we introduce for the first time to describe intra-class variations by multiple distributions. Then, multiple distributions representation learning(MDRL) is proposed to augment the pixel representations for semantic segmentation. Meanwhile, we design a class multiple distributions consistency strategy to construct discriminative multiple distribution representations of embedded pixels. Moreover, we put forward a multiple distribution semantic aggregation module to aggregate multiple distributions of the corresponding class to enhance pixel semantic information. Our approach can be seamlessly integrated into popular segmentation frameworks FCN/PSPNet/CCNet and achieve 5.61%/1.75%/0.75% mIoU improvements on ADE20K. Extensive experiments on the Cityscapes, ADE20K datasets have proved that our method can bring significant performance improvement.

READ FULL TEXT

page 7

page 8

research
08/26/2021

Mining Contextual Information Beyond Image for Semantic Segmentation

This paper studies the context aggregation problem in semantic image seg...
research
04/25/2018

Learning a Discriminative Feature Network for Semantic Segmentation

Most existing methods of semantic segmentation still suffer from two asp...
research
03/21/2023

Influencer Backdoor Attack on Semantic Segmentation

When a small number of poisoned samples are injected into the training d...
research
03/14/2022

CAR: Class-aware Regularizations for Semantic Segmentation

Recent segmentation methods, such as OCR and CPNet, utilizing "class lev...
research
01/11/2023

CARD: Semantic Segmentation with Efficient Class-Aware Regularized Decoder

Semantic segmentation has recently achieved notable advances by exploiti...
research
02/17/2015

Context Tricks for Cheap Semantic Segmentation

Accurate semantic labeling of image pixels is difficult because intra-cl...
research
10/05/2022

GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models

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

Please sign up or login with your details

Forgot password? Click here to reset