Deep multitask learning with label interdependency distillation for multicriteria street-level image classification

Aravena Pelizari, Patrick; Geiß, Christian; Groth, Sandro; Taubenböck, Hannes

doi:10.1016/j.isprsjprs.2023.09.001

Cited by 3 publications

(1 citation statement)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the context of urban building classification, the utilization of a multi-task learning modeling approach with five interdependent building labels consistently demonstrates superior accuracy and efficiency compared to both single-task learning and classical hard parameter sharing methods [39]. In agrarian contexts, prior studies utilizing multi-task deep convolutional neural networks have showcased marked advancements in delineating agricultural perimeters, field expanses, and cropping patterns [40,41].…”

Section: Introductionmentioning

confidence: 99%

Dual-Task Network for Terrace and Ridge Extraction: Automatic Terrace Extraction via Multi-Task Learning

Zhang,

Huang

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Terrace detection and ridge extraction from high-resolution remote sensing imagery are crucial for soil conservation and grain production on sloping land. Traditional methods use low-to-medium resolution images, missing detailed features and lacking automation. Terrace detection and ridge extraction are closely linked, with each influencing the other’s outcomes. However, most studies address these tasks separately, overlooking their interdependence. This research introduces a cutting-edge, multi-scale, and multi-task deep learning framework, termed DTRE-Net, designed for comprehensive terrace information extraction. This framework bridges the gap between terrace detection and ridge extraction, executing them concurrently. The network incorporates residual networks, multi-scale fusion modules, and multi-scale residual correction modules to enhance the model’s robustness in feature extraction. Comprehensive evaluations against other deep learning-based semantic segmentation methods using GF-2 terraced imagery from two distinct areas were undertaken. The results revealed intersection over union (IoU) values of 85.18% and 86.09% for different terrace morphologies and 59.79% and 73.65% for ridges. Simultaneously, we have confirmed that the connectivity of results is improved when employing multi-task learning for ridge extraction compared to directly extracting ridges. These outcomes underscore DTRE-Net’s superior capability in the automation of terrace and ridge extraction relative to alternative techniques.

show abstract

Section: Introductionmentioning

confidence: 99%

Dual-Task Network for Terrace and Ridge Extraction: Automatic Terrace Extraction via Multi-Task Learning

Zhang,

Huang

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

Applications of knowledge distillation in remote sensing: A survey

Himeur,

Aburaed,

Elharrouss

et al. 2025

Information Fusion

View full text Add to dashboard Cite

Comparison of Deep Learning Models and Feature Schemes for Detecting Pine Wilt Diseased Trees

Zhi,

Li,

Zhu

et al. 2024

Forests

View full text Add to dashboard Cite

Pine wilt disease (PWD) is a severe forest disease caused by the invasion of pine wood nematode (Bursaphelenchus xylophilus), which has caused significant damage to China’s forestry resources due to its short disease cycle and strong infectious ability. Benefiting from the development of unmanned aerial vehicle (UAV)-based remote sensing technology, the use of UAV images for the detection of PWD-infected trees has become one of the mainstream methods. However, current UAV-based detection studies mostly focus on multispectral and hyperspectral images, and few studies have focused on using red–green–blue (RGB) images for detection. This study used UAV-based RGB images to extract feature information using different color space models and then utilized semantic segmentation techniques in deep learning to detect individual PWD-infected trees. The results showed that: (1) The U-Net model realized the optimal image segmentation and achieved the highest classification accuracy with F1-score, recall, and Intersection over Union (IoU) of 0.9586, 0.9553, and 0.9221, followed by the DeepLabv3+ model and the feature pyramid networks (FPN) model. (2) The RGBHSV feature scheme outperformed both the RGB feature scheme and the hue saturation value (HSV) feature scheme, which were unrelated to the choice of the semantic segmentation techniques. (3) The semantic segmentation techniques in deep-learning models achieved superior model performance compared with traditional machine-learning methods, with the U-Net model obtaining 4.81% higher classification accuracy compared with the random forest model. (4) Compared to traditional semantic segmentation models, the newly proposed segment anything model (SAM) performed poorly in identifying pine wood nematode disease. Its success rate is 0.1533 lower than that of the U-Net model when using the RGB feature scheme and 0.2373 lower when using the HSV feature scheme. The results showed that the U-Net model using the RGBHSV feature scheme performed best in detecting individual PWD-infected trees, indicating that the proposed method using semantic segmentation technique and UAV-based RGB images to detect individual PWD-infected trees is feasible. The proposed method not only provides a cost-effective solution for timely monitoring forest health but also provides a precise means to conduct remote sensing image classification tasks.

show abstract

Deep multitask learning with label interdependency distillation for multicriteria street-level image classification

Cited by 3 publications

References 70 publications

Dual-Task Network for Terrace and Ridge Extraction: Automatic Terrace Extraction via Multi-Task Learning

Dual-Task Network for Terrace and Ridge Extraction: Automatic Terrace Extraction via Multi-Task Learning

Applications of knowledge distillation in remote sensing: A survey

Comparison of Deep Learning Models and Feature Schemes for Detecting Pine Wilt Diseased Trees

Contact Info

Product

Resources

About