Deep Transfer Learning for Land Use and Land Cover Classification: A Comparative Study

Abstract

Efficiently implementing remote sensing image classification with high spatial resolution imagery can provide significant value in land use and land cover (LULC) classification. The new advances in remote sensing and deep learning technologies have facilitated the extraction of spatiotemporal information for LULC classification. Moreover, diverse disciplines of science, including remote sensing, have utilised tremendous improvements in image classification involving convolutional neural networks (CNNs) with transfer learning. In this study, instead of training CNNs from scratch, the transfer learning was applied to fine-tune pre-trained networks Visual Geometry Group (VGG16) and Wide Residual Networks (WRNs), by replacing the final layers with additional layers, for LULC classification using the red–green–blue version of the EuroSAT dataset. Moreover, the performance and computational time are compared and optimised with techniques such as early stopping, gradient clipping, adaptive learning rates, and data augmentation. The proposed approaches have addressed the limited-data problem, and very good accuracies were achieved. The results show that the proposed method based on WRNs outperformed the previous best results in terms of computational efficiency and accuracy, by achieving 99.17%.

LPIN: A Lightweight Progressive Inpainting Network for Improving the Robustness of Remote Sensing Images Scene Classification

“…In our following work, we plan to carry out image inpainting research using the history RS images with temporal information, obtain real RS images from satellites, adopt more deep learning regularization techniques in the training process-such as early stopping [23] which we believe can reduce overfitting-and enhance the generalization ability of our model and further lower the time consumption.…”

“…The negative SSIM overcomes this drawback by measuring the differences in brightness, contrast and structure of two images, which makes it a more effective reconstruction loss function. VGG16 and ResNet50 are two well-performed feature extractors [23]. Different features extracted from them are used to calculate the content and style loss and compare the inpainting results, which are shown in Table 10.…”

“…For instance, the overall accuracy (OA) is 94.87% [16] on the NWPU-RESISC45 dataset [20] and 96.05% [16] on the Aerial Image Dataset (AID) [21], both with a training ratio of only 20%. Moreover, the RS image classifications using the red-green-blue band of EuroSAT dataset [22] achieves an accuracy of 99.17% via deep transfer learning [23].…”

Unmanned Aerial Vehicle (UAV)-Based Remote Sensing for Early-Stage Detection of Ganoderma

“…For this purpose, the dataset was randomly split into two sets: 60% for model training and 40% for model testing. The testing dataset was also used for early stopping during model training in order to avoid model overfitting [63]. The total classification accuracy for each disease level was calculated by comparing the model predicted and actual disease level.…”

A Two-Stage Pansharpening Method for the Fusion of Remote-Sensing Images

“…PS with spatial and spectral gradient difference-induced nonconvex sparsity priors (PSSGDNSP) [43] uses the eigenband correlation of MS images to process MS images as third-order tensors. In addition, there are some fusion methods based on DL [44][45][46][47][48][49][50][51][52][53][54]. The DL method's main disadvantages are the lack of ideal PS samples for training, it relies on generating reference samples from unlabeled real data (such as MS images).…”