A Weakly Supervised Semantic Segmentation Model of Maize Seedlings and Weed Images Based on Scrawl Labels
Open Access
Abstract
The task of semantic segmentation of maize and weed images using fully supervised deep learning models requires a large number of pixel-level mask labels, and the complex morphology of the maize and weeds themselves can further increase the cost of image annotation. To solve this problem, we proposed a Scrawl Label-based Weakly Supervised Semantic Segmentation Network (SL-Net). SL-Net consists of a pseudo label generation module, encoder, and decoder. The pseudo label generation module converts scrawl labels into pseudo labels that replace manual labels that are involved in network training, improving the backbone network for feature extraction based on the DeepLab-V3+ model and using a migration learning strategy to optimize the training process. The results show that the intersection over union of the pseudo labels that are generated by the pseudo label module with the ground truth is 83.32%, and the cosine similarity is 93.55%. In the semantic segmentation testing of SL-Net for image seedling of maize plants and weeds, the mean intersection over union and average precision reached 87.30% and 94.06%, which is higher than the semantic segmentation accuracy of DeepLab-V3+ and PSPNet under weakly and fully supervised learning conditions. We conduct experiments to demonstrate the effectiveness of the proposed method.Keywords
Funding Information
- National Natural Science Foundation of China (31901399, 2021YFD1500204, 2022YFD2002303-01, JYTMS20231303)
- Sub-project of the Fourteenth-Five Year National Key R&D Plan (31901399, 2021YFD1500204, 2022YFD2002303-01, JYTMS20231303)
- Sub-project of National Key R&D Plan (31901399, 2021YFD1500204, 2022YFD2002303-01, JYTMS20231303)
- Liaoning Province Innovation Capability Enhancement Joint Fund Project (31901399, 2021YFD1500204, 2022YFD2002303-01, JYTMS20231303)
This publication has 26 references indexed in Scilit:
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation2018
- A brief introduction to weakly supervised learningNational Science Review, 2017
- Pyramid Scene Parsing Network2017
- What’s the Point: Semantic Segmentation with Point Supervision2016
- ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation2016
- BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation2015
- Transfer Learning for Visual Categorization: A SurveyIEEE Transactions on Neural Networks and Learning Systems, 2014
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- "GrabCut"ACM Transactions on Graphics, 2004
- A Threshold Selection Method from Gray-Level HistogramsIEEE Transactions on Systems, Man, and Cybernetics, 1979