An Optimization Method of Deep Transfer Learning for Vegetation Segmentation under Rainy and Dry Season Differences in a Dry Thermal Valley
Open Access
Abstract
Deep learning networks might require re-training for different datasets, consuming significant manual labeling and training time. Transfer learning uses little new data and training time to enable pre-trained network segmentation in relevant scenarios (e.g., different vegetation images in rainy and dry seasons); however, existing transfer learning methods lack systematicity and controllability. So, an MTPI method (Maximum Transfer Potential Index method) was proposed to find the optimal conditions in data and feature quantity for transfer learning (MTPI conditions) in this study. The four pre-trained deep networks (Seg-Net (Semantic Segmentation Networks), FCN (Fully Convolutional Networks), Mobile net v2, and Res-Net 50 (Residual Network)) using the rainy season dataset showed that Res-Net 50 had the best accuracy with 93.58% and an WIoU (weight Intersection over Union) of 88.14%, most worthy to transfer training in vegetation segmentation. By obtaining each layer’s TPI performance (Transfer Potential Index) of the pre-trained Res-Net 50, the MTPI method results show that the 1000-TDS and 37-TP were estimated as the best training speed with the smallest dataset and a small error risk. The MTPI transfer learning results show 91.56% accuracy and 84.86% WIoU with 90% new dataset reduction and 90% iteration reduction, which is informative for deep networks in segmentation tasks between complex vegetation scenes.Keywords
Funding Information
- National Natural Science Foundation of China (52222903, 41977007, BHT/0869)
- China Three Gorges Corporation-funded “Research on Soil Improvement, Plant Selection, and Slope Ecological Restoration Techniques in the Arid Hot Valley Area of the Baihetan Hydropower Station” (52222903, 41977007, BHT/0869)
This publication has 56 references indexed in Scilit:
- A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests RecognitionSensors, 2017
- Temporal Vegetation Modelling Using Long Short-Term Memory Networks for Crop Identification from Medium-Resolution Multi-spectral Satellite Images2017
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Automated big security text pruning and classification2016
- Deep Residual Learning for Image Recognition2016
- Fully Convolutional Networks for Semantic SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Review of research on the vegetation and environment of dry-hot valleys in YunnanBiodiversity Science, 2016
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Detecting changes in vegetation trends using time series segmentationRemote Sensing of Environment, 2015
- Content Based Image Retrieval and Classification using speeded-up robust features (SURF) and grouped bag-of-visual-words (GBoVW)2013