Pyramid Geometric Consistency Learning For Semantic Segmentation
作者：
Highlights：
• highlights
• We propose a supervised pyramid consistency learning framework in semantic segmentation. In the data preparation stage, it can obtain the overlap between different views. During the training process, corresponding pair and label information are used to improve the segmentation results at the same time. Method in this article does not require additional calculation and has a stable performance improvement compared to the baseline on main public datasets.
• We designed CCM for supervising intermediate features while considering both the similarity of pixel-level and regional-level features. We also introduced cross-layer feature consistency learning. The experimental results show that the pyramid-like CCM can achieve better accuracy.
• This paper also designs a mixed loss function optimized by labels and pseudo labels. Using the similarity between the middle layer and the output features, PGC can assist the existing semantic segmentation model to achieve better results.
摘要
highlights•We propose a supervised pyramid consistency learning framework in semantic segmentation. In the data preparation stage, it can obtain the overlap between different views. During the training process, corresponding pair and label information are used to improve the segmentation results at the same time. Method in this article does not require additional calculation and has a stable performance improvement compared to the baseline on main public datasets.•We designed CCM for supervising intermediate features while considering both the similarity of pixel-level and regional-level features. We also introduced cross-layer feature consistency learning. The experimental results show that the pyramid-like CCM can achieve better accuracy.•This paper also designs a mixed loss function optimized by labels and pseudo labels. Using the similarity between the middle layer and the output features, PGC can assist the existing semantic segmentation model to achieve better results.
论文关键词：Semantic segmentation,Consistency learning,Supervised contrastive learning
论文评审过程：Received 2 February 2022, Revised 24 June 2022, Accepted 4 September 2022, Available online 9 September 2022, Version of Record 21 September 2022.
论文官网地址：https://doi.org/10.1016/j.patcog.2022.109020
