Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite Images

Desai, Shasvat Mukeshkumar; Ghose, Debasmita

doi:10.1109/wacv51458.2022.00155

Cited by 27 publications

(23 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have analyzed datasets with videos of objects in the cities shooting from UAV's on-board cameras. Finally, our dataset was collected our based-on parts of three datasets: VisDrone 2019 [31], Drone Vehicle Dataset [32], and DTB70 [33] with included pre-labeled annotations of bounding boxes. In our task, we collected sequences of objects in sideshot scope mode from the height level (15 -45 meters).…”

Section: Resultsmentioning

confidence: 99%

“…According to our hypothesis, the memorybased methods will be highly effective for the task of object tracking via the unmanned aerial vehicle, because on-road objects regularly move along a strictly trajectories from the UAV's shooting view. To validate our idea, we have collected the dataset based on image sequences shooted from the unmanned aerial vehicles shouted: VisDrone 2019 [31], Drone Vehicle Dataset [32], and DTB70 [33] with the corresponding labels. Finally, we have provided the robustness analysis of S-Y-biLST compared to LYOLOv4eff [34], ROLO [35] and DeepSort.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust S-Y-biLSTM object tracking method for on-road objects shoot from an unmanned aerial vehicle

Saetchnikov

Skakun

Tcherniavskaia

2022

2022 IEEE 9th International Workshop on Metrology for AeroSpace (MetroAeroSpace)

View full text Add to dashboard Cite

being one of the most challenging tasks in computer vision dynamical object tracking problems have faced additional issues regarding the unmanned aerial vehicle. In particular, image degradation, uneven object intensity, variety in object sizes, etc. In this paper, we proposed the implementation of the S-Y-biLSTM technique for on-road object shooting from an unmanned aerial vehicle. The training and testing process of the proposed network was performed based on the dataset of on-road objects shouted at the height of 15-45 meters.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Robust S-Y-biLSTM object tracking method for on-road objects shoot from an unmanned aerial vehicle

Saetchnikov

Skakun

Tcherniavskaia

2022

2022 IEEE 9th International Workshop on Metrology for AeroSpace (MetroAeroSpace)

View full text Add to dashboard Cite

show abstract

“…Wang et al presented an iterative contrastive network for remote sensing image semantic segmentation, which can continuously learn more potential information from labeled samples and generate better pseudo-labels for unlabeled data [34]. S. Desai et al employed active learning techniques to generate pseudo-labels from a small set of labeled examples which are used to augment the labeled training set, and enhanced the performance of remote sensing semantic segmentation network [35].…”

Section: Semi-supervised and Weakly Supervised Deep Learning Methodsmentioning

confidence: 99%

SW-GAN: Road Extraction from Remote Sensing Imagery Using Semi-Weakly Supervised Adversarial Learning

Chen

Peng

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Road networks play a fundamental role in our daily life. It is of importance to extract the road structure in a timely and precise manner with the rapid evolution of urban road structure. Recently, road network extraction using deep learning has become an effective and popular method. The main shortcoming of the road extraction using deep learning methods lies in the fact that there is a need for a large amount of training datasets. Additionally, the datasets need to be elaborately annotated, which is usually labor-intensive and time-consuming; thus, lots of weak annotations (such as the centerline from OpenStreetMap) have accumulated over the past a few decades. To make full use of the weak annotations, we propose a novel semi-weakly supervised method based on adversarial learning to extract road networks from remote sensing imagery. Our method uses a small set of pixel-wise annotated data and a large amount of weakly annotated data for training. The experimental results show that the proposed approach can achieve a maintained performance compared with the methods that use a large number of full pixel-wise annotations while using less fully annotated data.

show abstract

“…Segmentation has found widespread application in the domain of satellite imaging, including but not limited to image augmentation, object detection, change detection, geolocalization, and cross-view image synthesis [7]. Dimensionality reduction in satellite images via segmentation has many applications in satellite image processing, including road extraction, building extraction, which is important for urban planning, and climate change detection, which is essential in sustainable development and forest preservation research.…”

Section: A Satellite Image Segmentationmentioning

confidence: 99%

“…Considering the cumbersome task of satellite image segmentation, research infrequently focuses on extracting multiple objects in a highly representative and diverse labeled training set. Desai et al [7] proposed to use an active learning-based sampling strategy to overcome the challenge of labeling a highly representative set of training data. Active learning has been practiced before in semantic segmentation to detect the most informative patches of the input image.…”

Section: ) Weak Object Extractionmentioning

confidence: 99%

GAN-Based Satellite Imaging: A Survey on Techniques and Applications

et al. 2022

View full text Add to dashboard Cite

Satellite image analysis is widely used in many real-time applications, from agriculture to the military. Due to the wide range of Generative Adversarial Network (GAN) applications in multiple areas of satellite imaging, a comprehensive review is required in this area. This paper takes the first step in this direction by categorizing the GAN-based satellite imaging research using seven considerations. We discuss not only the challenges but also future research trends and directions. Among the major findings, we have observed increasing componentization and modularization of GANs to be used as elements of larger systems. In addition to the GAN types used exclusively in each application, we demonstrate the deep neural network architectures used as the generator structure. Eventually, we summarize the results and evaluate the significant impact of GANs on improving performance compared to traditional approaches.

show abstract

Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite Images

Cited by 27 publications

References 36 publications

Robust S-Y-biLSTM object tracking method for on-road objects shoot from an unmanned aerial vehicle

Robust S-Y-biLSTM object tracking method for on-road objects shoot from an unmanned aerial vehicle

SW-GAN: Road Extraction from Remote Sensing Imagery Using Semi-Weakly Supervised Adversarial Learning

GAN-Based Satellite Imaging: A Survey on Techniques and Applications

Contact Info

Product

Resources

About