.png){kind=icon}
返回
Learning Ordinality in Semantic Segmentation
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2025.3537601.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Semantic segmentation consists of predicting a semantic label for each image pixel. While existing deep learning approaches achieve high accuracy, they often overlook the ordinal relationships between classes, which can provide critical domain knowledge (e.g., the pupil lies within the iris, and lane markings are part of the road). This paper introduces novel methods for spatial ordinal segmentation that explicitly incorporate these inter-class dependencies. By treating each pixel as part of a structured image space rather than as an independent observation, we propose two regularization terms and a new metric to enforce ordinal consistency between neighboring pixels. Two loss regularization terms and one metric are proposed for structural ordinal segmentation, which penalizes predictions of non-ordinal adjacent classes. Five biomedical datasets and multiple configurations of autonomous driving datasets demonstrate the efficacy of the proposed methods. Our approach achieves improvements in ordinal metrics and enhances generalization, with up to a 15.7% relative increase in the Dice coefficient. Importantly, these benefits come without additional inference time costs. This work highlights the significance of spatial ordinal relationships in semantic segmentation and provides a foundation for further exploration in structured image representations.
Keyword:
Semantic segmentation
Encoding
Semantics
Knowledge engineering
Diseases
Probability distribution
Image classification
Costs
Convolutional neural networks
Autonomous vehicles
Ordinal segmentation
semantic segmentation
domain knowledge
deep neural network
autonomous driving
scene parsing
deep learning
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Periplaneta fuliginosa densovirus nonstructural protein NS1 contains an endonuclease activity that is regulated by its phosphorylation.png)
Virology
VirologyIF0
PREAI
分享收藏分享收藏
Electrochemically assisted micro localized grafting of aptamers in a microchannel engraved in fluorinated thermoplastic polymer Dyneon THVRSC Advances
RSC AdvancesIF0
PREAI
分享收藏
查看更多内容