Hao Wang

Dr. Hao Wang

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 December 2019 in ISPRS Journal of Photogrammetry and Remote Sensing
Verified
Journal Article
Closed access
CTChao Tao
Chao Tao
JQJi Qi
Ji Qi
YLYansheng Li
Yansheng Li
HWHao Wang
Hao Wang
Haifeng LiHaifeng Li
Haifeng Li

7 December 2020 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
Chao TaoChao Tao
Chao Tao
JQJi Qi
Ji Qi
WLWeipeng Lu
Weipeng Lu
HWHao Wang
Hao Wang
Haifeng LiHaifeng Li
Haifeng Li
With the development of deep learning, supervised learning methods perform well in remote sensing image (RSI) scene classification. However, supervised learning requires a huge number of annotated data for training. When labeled samples are not sufficient, the most common solution is to fine-tune the pretraining models using a large natural image data set (e.g., ImageNet). However, this learning paradigm is not a panacea, especially when the target RSIs (e.g., multispectral and hyperspectral data) have different imaging mechanisms from RGB natural images. To solve this problem, we introduce a new self-supervised learning (SSL) mechanism to obtain the high-performance pretraining model for RSI scene classification from large unlabeled data. Experiments on three commonly used RSI scene classification data sets demonstrated that this new learning paradigm outperforms the traditional dominant ImageNet pretrained model. Moreover, we analyze the impacts of several factors in SSL on RSI scene classification, including the choice of self-supervised signals, the domain difference between the source and target data sets, and the amount of pretraining data. The insights distilled from this work can help to foster the development of SSL in the remote sensing community. Since SSL could learn from unlabeled massive RSIs, which are extremely easy to obtain, it will be a promising way to alleviate dependence on labeled samples and thus efficiently solve many problems, such as global mapping.

25 August 2022 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
HWHao Wang
Hao Wang
Chao TaoChao Tao
Chao Tao
JQJi Qi
Ji Qi
RXRong Xiao
Rong Xiao
Haifeng LiHaifeng Li
Haifeng Li
Reducing the feature distribution shift caused by the factor of visual-environment changes, named visual-environment changes (VE-changes), is a hot issue in domain adaptation learning. However, in the semantic segmentation task of remote sensing imageries, besides VE-changes, the change of semantic-scene changes (SS-changes) is another factor raising the domain gap, which brings the label distribution shift. For example, although urban and rural share the same landcover label, there is still a gap in label distribution. If there is little relation that can be found in neither feature nor label space, forcibly adapting to a new domain could have a high risk of negative transfer. Hence, we propose a new Transitive Domain Adaptation method for Remote Sensing (TDARS) images. First, we introduce an intermediate domain to enlarge the relation between the given source and target domains. Second, we learn from primary and nonprimary confident classes to increase the likelihood of transferring valuable information. As a result, TDARS enables the given source and target domains to be connected through the selected intermediate domain and performs effective knowledge transfer among all domains. The proposed method is evaluated on three domain adaptation datasets of remote sensing images. Extensive experiments show that the approach can effectively handle the domain shift problem from remote sensing images compared to other state-of-the-art domain adaptation methods.

1 July 2019
Verified
Conference Paper
Closed access
HWHao Wang
Hao Wang
CTChao Tao
Chao Tao
JQJi Qi
Ji Qi
HLHaiFeng Li
HaiFeng Li
YTYuQi Tang
YuQi Tang
Though Hyperspectral Image (HSI) Classification has been extensively investigated over recent decades, it is still a challenge task especially when the number of labeled samples is extremely limited. In this paper, we overcome this challenge by using synthetic samples, and proposed a semi-supervised variational Generative Adversarial Networks(GANs) for this purpose. Compared to the conditional GAN which is recently used for generating samples for HSI classification, the proposed approach has two novel aspects. First, we extend the classic variational generative adversarial network to the semi-supervised context through an ensemble prediction technique. By this way, our model can be trained using limited labeled samples (only 5 samples per class) with a large number of unlabeled samples. Second, we adopt an encoder-decoder network to explicitly learn the relationship between the latent space and the real image space. This property enables our model producing diverse samples by simply varying some latent parameters, which is desirable for enriching the training dataset. We have shown that the proposed model can achieve better and robust performance for HSI classification compared to conditional GAN, especially when the labeled data is limited.

24 February 2020 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
Chao TaoChao Tao
Chao Tao
HWHao Wang
Hao Wang
JQJi Qi
Ji Qi
Haifeng LiHaifeng Li
Haifeng Li
Although hyperspectral image (HSI) classification is extensively investigated, this task remains challenging when the number of labeled samples is extremely limited. In this paper, we overcome this challenge by using synthetic samples and proposing semi-supervised variational generative adversarial networks (GANs). In contrast to conditional GAN (previously used for the generation of HSI samples), the proposed approach has two novel aspects. First, an encoder-decoder network is extended to the semi-supervised context using an ensemble prediction technique. Through this technique, our deep generative model can be trained using limited labeled samples (only five samples per class) with a large number of unlabeled samples. Second, we build a collaborative relationship between the generation network and the classification network. This property enables that our model can produce meaningful samples which can contribute to the final classification. The experiments on four HSI benchmarks demonstrate that the proposed model can achieve an increase of >10% in overall classification accuracy compared with the baseline model without using the generated sample. We also show that the proposed model can achieve better and more robust performance for HSI classification than other generative methods as well as semi-supervised methods, especially when the labeled data are limited.

18 May 2020 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
Chao TaoChao Tao
Chao Tao
WLWeipeng Lu
Weipeng Lu
JQJi Qi
Ji Qi
HWHao Wang
Hao Wang
Remote sensing image (RSI) scene classification (RSISC) is a fundamental problem for understanding high-resolution RSIs. More recently, deep learning methods, especially convolutional neural networks (CNNs), and large data sets have greatly promoted the RSISC. However, deep learning methods rely heavily on the visual features extracted from the patches cropped from original RSIs, so the intraclass diversity and interclass similarity are two big challenges. To address these problems, in this letter, we propose a spatial information considered model to learn more discriminative features. By combining CNN and recurrent neural network, the proposed method can exploit both local and long-range spatial relation information to enhance the representational ability of the learned features. As the initial visual features of a single patch are transformed into higher-level features with spatial information, the proposed method achieves more accurate scene classification. Besides, we present an RSISC data set named as CSU-RSISC10 data set to preserve the spatial information between scenes in a new way of organization. Experiments demonstrate that the proposed method outperforms other three state-of-the-art methods in scene classification using CSU-RSISC10 data set.