Can I read GuidedMix-Net: Semi-supervised Semantic Segmentation by Using Labeled Images as Reference on EtoBox?

GuidedMix-Net: Semi-supervised Semantic Segmentation by Using Labeled Images as Reference by Tu, Peng; Huang, Yawen; Zheng, Feng; He, Zhenyu; Cao, Liujun; Shao, Ling is a scholarly article available to read on EtoBox.

What is GuidedMix-Net: Semi-supervised Semantic Segmentation by Using Labeled Images as Reference about?

Semi-supervised learning is a challenging problem which aims to construct a model by learning from limited labeled examples. Numerous methods for this task focus on utilizing the predictions of unlabeled instances consistency alone to regularize networks. However, treating labeled and unlabeled data separately often leads to the discarding of mass prior knowledge learned from the labeled examples. %, and failure to mine the feature interaction between the labeled and unlabeled image pairs. In this paper, we propose a novel method for semi-supervised semantic segmentation named GuidedMix-Net, by leveraging labeled information to guide the learning of unlabeled instances. Specifically, GuidedMix-Net employs three operations: 1) interpolation of similar labeled-unlabeled image pairs; 2) transfer of mutual information; 3) generalization of pseudo masks. It enables segmentation models can learning the higher-quality pseudo masks of unlabeled data by transfer the knowledge from labeled samples to unlabeled data. Along with supervised learning for labeled data, the prediction of unlabeled data is jointly learned with the generated pseudo masks from the mixed data. Extensive experiments on

Author

Tu, Peng; Huang, Yawen; Zheng, Feng; He, Zhenyu; Cao, Liujun; Shao, Ling

Published

2021

Language

EN