Class-Aware Feature Regularization for Semantic Segmentation

No Thumbnail Available
File version
Author(s)
Deng, Z
Tang, X
Zhang, Z
Xie, J
Zhang, Weichuan
Griffith University Author(s)
Primary Supervisor
Other Supervisors
Editor(s)
Date
2023
Size
File type(s)
Location
License
Abstract

In this paper, to address the problem of intra-class consistency and inter-class variation in the deep convolutional neural network (CNN) based methods for semantic segmentation of images, we propose a class-aware feature regularization strategy to revise the features extracted by a deep convolutional neural network, without any change of the original network structure. A pixel-context similarity term is proposed to measure the consistency between feature vectors of pixels and class centers, which guarantees the intra-class consistency of pixels in the interior of an object and is supervised by a One-Hot label to preserve the inter-class variation of different objects. Based on the similarity term, we design a lightweight and efficient plug-in loss term to ensure that the features yielded by a deep CNN possess the quality of intra-class consistency and inter-class variation. As our ideal can be fulfilled effectively by the proposed plug-in loss term, we can simply incorporate it into a CNN-based segmentation model without changing the model structure. The effectiveness of the proposed strategy is proved by incorporating the loss term into some state-of-the-art segmentation models on Cityscapes and ADE20K datasets.

Journal Title
Conference Title
ICCPR '23: Proceedings of the 2023 12th International Conference on Computing and Pattern Recognition
Book Title
Edition
Volume
Issue
Thesis Type
Degree Program
School
Publisher link
Patent number
Funder(s)
Grant identifier(s)
Rights Statement
Rights Statement
Item Access Status
Note
Access the data
Related item(s)
Subject
Deep learning
Neural networks
Artificial intelligence
Image processing
Pattern recognition
Persistent link to this record
Citation
Deng, Z; Tang, X; Zhang, Z; Xie, J; Zhang, W, Class-Aware Feature Regularization for Semantic Segmentation, ICCPR '23: Proceedings of the 2023 12th International Conference on Computing and Pattern Recognition, 2023, pp. 362-366