We propose in this thesis to build up a collaboration between a deep neural network and a human in the loop to swiftly collect accurate segmentation maps of remote sensing images. In a nutshell, the user iteratively interacts with the network to correct its initially flawed predictions. Concretely, these interactions are annotations representing the semantic labels. Our contributions are fourfold. First, we propose two interactive learning schemes to integrate user inputs into deep neural networks. The first one concatenates the user annotations with the other inputs of the network (e.g. RGB image). We apply it both to convolutional architectures and to Transformers. The second one uses the annotations as a sparse ground-truth to retrain th...
The performance of deep neural networks depends on the accuracy of labeled samples, as they usually ...
Existing deep learning-based remote sensing images semantic segmentation methods require large-scale...
This work deals with the challenge of semantic segmentation based on deep learning methods in the ca...
Nous proposons dans cette thèse de mettre en place une collaboration entre un réseau de neurones pro...
National audienceIn this paper, a novel method to tackle semantic segmentation of very high resoluti...
International audienceThis work investigates the use of deep fully convolutional neural networks (DF...
International audienceThis paper explores different aspects of semantic segmentation of remote sensi...
Semantic segmentation is a critical problem for many remote sensing (RS) image applications. Benefit...
Semantic segmentation requires methods capable of learning high-level features while dealing with la...
Training convolutional neural networks (CNNs) for very high-resolution images requires a lar...
Transfer learning is a powerful way to adapt existing deep learning models to new emerging use-cases...
Semantic segmentation of remote sensing (RS) images, which is a fundamental research topic, classifi...
With the development of deep learning, the performance of image semantic segmentation in remote sens...
Training convolutional neural networks (CNNs) for very high-resolution images requires a large quant...
In the recent years, remote sensing has faced a huge evolution. The constantly growing availability ...
The performance of deep neural networks depends on the accuracy of labeled samples, as they usually ...
Existing deep learning-based remote sensing images semantic segmentation methods require large-scale...
This work deals with the challenge of semantic segmentation based on deep learning methods in the ca...
Nous proposons dans cette thèse de mettre en place une collaboration entre un réseau de neurones pro...
National audienceIn this paper, a novel method to tackle semantic segmentation of very high resoluti...
International audienceThis work investigates the use of deep fully convolutional neural networks (DF...
International audienceThis paper explores different aspects of semantic segmentation of remote sensi...
Semantic segmentation is a critical problem for many remote sensing (RS) image applications. Benefit...
Semantic segmentation requires methods capable of learning high-level features while dealing with la...
Training convolutional neural networks (CNNs) for very high-resolution images requires a lar...
Transfer learning is a powerful way to adapt existing deep learning models to new emerging use-cases...
Semantic segmentation of remote sensing (RS) images, which is a fundamental research topic, classifi...
With the development of deep learning, the performance of image semantic segmentation in remote sens...
Training convolutional neural networks (CNNs) for very high-resolution images requires a large quant...
In the recent years, remote sensing has faced a huge evolution. The constantly growing availability ...
The performance of deep neural networks depends on the accuracy of labeled samples, as they usually ...
Existing deep learning-based remote sensing images semantic segmentation methods require large-scale...
This work deals with the challenge of semantic segmentation based on deep learning methods in the ca...