TE-SAGAN: An Improved Generative Adversarial Network for Remote Sensing Super-Resolution Images

Xu, Yongyang; Luo, Wei; Hu, Anna; Xie, Zhen; Xie, Xuejing; Tao, Liufeng

doi:10.3390/rs14102425

Cited by 43 publications

(28 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning techniques for blind image super-resolution: A high-scale multi-domain perspective evaluation deep learning (DL) and deep neural networks (DNNs) [21], a significant number of strategies have been proposed addressing SR via DL/DNNs as reported in recent secondary studies [17,11]. Among the DL techniques, convolutional neural networks (CNNs) [22,23,24,13], generative adversarial networks (GAN) [25,26,12,14], and attention-based networks [27,28,15] have been employed to solve image SR problems.…”

Section: Arxiv:230609426v1 [Eessiv] 15 Jun 2023mentioning

confidence: 99%

“…Medical imaging [1,2,3,4], internet video delivery [5,6,7], surveillance and security via person identification [8,9,10], and remote sensing [11,12,13,14,15,16] are just some examples of real-world applications where image super-resolution (SR) has been used. In SR, we aim at recovering high-resolution 1 (HR) images from low-resolution (LR) ones.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluating Deep Learning Techniques for Blind Image Super-Resolution within a High-Scale Multi-Domain Perspective

de Santiago Júnior

2023

View full text Add to dashboard Cite

Despite several solutions and experiments have been conducted recently addressing image super-resolution (SR), boosted by deep learning (DL), they do not usually design evaluations with high scaling factors. Moreover, the datasets are generally benchmarks which do not truly encompass significant diversity of domains to proper evaluate the techniques. It is also interesting to remark that blind SR is attractive for real-world scenarios since it is based on the idea that the degradation process is unknown, and, hence, techniques in this context rely basically on low-resolution (LR) images. In this article, we present a high-scale (8×) experiment which evaluates five recent DL techniques tailored for blind image SR: Adaptive Pseudo Augmentation (APA), Blind Image SR with Spatially Variant Degradations (BlindSR), Deep Alternating Network (DAN), FastGAN, and Mixture of Experts Super-Resolution (MoESR). We consider 14 datasets from five different broader domains (Aerial, Fauna, Flora, Medical, and Satellite), and another remark is that some of the DL approaches were designed for single-image SR but others not. Based on two no-reference metrics, NIQE and the transformer-based MANIQA score, MoESR can be regarded as the best solution although the perceptual quality of the created high-resolution (HR) images of all the techniques still needs to improve.

show abstract

Section: Arxiv:230609426v1 [Eessiv] 15 Jun 2023mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Evaluating Deep Learning Techniques for Blind Image Super-Resolution within a High-Scale Multi-Domain Perspective

de Santiago Júnior

2023

View full text Add to dashboard Cite

show abstract

“…Besides these methods, integrating the clustering and optimization of neural networks also can learn good representations [27][28][29][30]. In the past two years, self-supervised learning methods have been widely applied to the area of remote sensing and have reached remarkable performance [52][53][54][55][56][57][58][59].…”

Section: Related Workmentioning

confidence: 99%

Improving Image Clustering through Sample Ranking and Its Application to Remote Sensing Images

Qiu

2022

Remote Sensing

View full text Add to dashboard Cite

Image clustering is a very useful technique that is widely applied to various areas, including remote sensing. Recently, visual representations by self-supervised learning have greatly improved the performance of image clustering. To further improve the well-trained clustering models, this paper proposes a novel method by first ranking samples within each cluster based on the confidence in their belonging to the current cluster and then using the ranking to formulate a weighted cross-entropy loss to train the model. For ranking the samples, we developed a method for computing the likelihood of samples belonging to the current clusters based on whether they are situated in densely populated neighborhoods, while for training the model, we give a strategy for weighting the ranked samples. We present extensive experimental results that demonstrate that the new technique can be used to improve the state-of-the-art image clustering models, achieving accuracy performance gains ranging from 2.1% to 15.9%. Performing our method on a variety of datasets from remote sensing, we show that our method can be effectively applied to remote sensing images.

show abstract

“…These generative models mainly include Boltzmann machines [36][37][38], autoencoders [39] and generative adversarial networks (GAN) [40][41][42][43]. In [44], an improved generative adversarial network was applied to the super-resolution processing of RSI.…”

Section: Related Workmentioning

confidence: 99%

Clustering-Based Representation Learning through Output Translation and Its Application to Remote-Sensing Images

Garibaldi

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

In supervised deep learning, learning good representations for remote-sensing images (RSI) relies on manual annotations. However, in the area of remote sensing, it is hard to obtain huge amounts of labeled data. Recently, self-supervised learning shows its outstanding capability to learn representations of images, especially the methods of instance discrimination. Comparing methods of instance discrimination, clustering-based methods not only view the transformations of the same image as “positive” samples but also similar images. In this paper, we propose a new clustering-based method for representation learning. We first introduce a quantity to measure representations’ discriminativeness and from which we show that even distribution requires the most discriminative representations. This provides a theoretical insight into why evenly distributing the images works well. We notice that only the even distributions that preserve representations’ neighborhood relations are desirable. Therefore, we develop an algorithm that translates the outputs of a neural network to achieve the goal of evenly distributing the samples while preserving outputs’ neighborhood relations. Extensive experiments have demonstrated that our method can learn representations that are as good as or better than the state of the art approaches, and that our method performs computationally efficiently and robustly on various RSI datasets.

show abstract

TE-SAGAN: An Improved Generative Adversarial Network for Remote Sensing Super-Resolution Images

Cited by 43 publications

References 51 publications

Evaluating Deep Learning Techniques for Blind Image Super-Resolution within a High-Scale Multi-Domain Perspective

Evaluating Deep Learning Techniques for Blind Image Super-Resolution within a High-Scale Multi-Domain Perspective

Improving Image Clustering through Sample Ranking and Its Application to Remote Sensing Images

Clustering-Based Representation Learning through Output Translation and Its Application to Remote-Sensing Images

Contact Info

Product

Resources

About