A Pseudo-Dual Self-Rectification Framework for Semantic Segmentation

Semantic segmentation has achieved remarkable success in various applications. However, the training process for such techniques necessitates a significant amount of labeled data. Although semi-supervised frameworks can alleviate this issue, traditional approaches typically require multiple baseline...

Full description

Saved in:
Bibliographic Details
Main Authors: Hao, Huazheng, Xiao, Hui, Dong, Li, Yan, Diqun, Liang, Dongtai, Zhuang, Jiayan, Peng, Chengbin
Format: Conference Proceeding
Language:English
Subjects:
Benchmark testing
Computational modeling
Data models
Error rectification
Prototypes
Semantic segmentation
Semantics
Semi-supervised learning
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Semantic segmentation has achieved remarkable success in various applications. However, the training process for such techniques necessitates a significant amount of labeled data. Although semi-supervised frameworks can alleviate this issue, traditional approaches typically require multiple baseline models to form a dual model. To allow a semi-supervised semantic segmentation framework to be used in robotic systems with precious computation and memory resources, we propose a framework utilizing a single baseline model only. The overall framework is composed of three parts: an encoder, a shallow decoder, and a deep decoder. It distills knowledge from the ensemble of two decoders to improve the encoder, which can implicitly form a pseudo-dual model. It also calculates class-wise likelihoods according to the similarity between features and class prototypes learned from different decoders and rectifies low-confidence pseudo-labels. Our framework outperforms state-of-the-art frameworks on benchmark datasets with a significant amount of decrease in using computing resources.
ISSN:1945-788X
DOI:10.1109/ICME55011.2023.00077