Domain Adaptation for Convolutional Neural Networks-Based Remote Sensing Scene Classification

Song, Shaoyue; Yu, Hongkai; Miao, Zhenjiang; Zhang, Qiang; Lin, Yuewei; Wang, Song

doi:10.1109/lgrs.2019.2896411

Cited by 111 publications

(55 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, a backbone CNN architecture is considered in order to generate the corresponding feature embedding space for the input images. In this work, we make use of the ResNet [56] architecture due to its good performance to classify RS scenes [57]. Second, a new loss function, which contains a joint CE term and an SNCA term, is used to optimize the proposed model in order to address the within-class diversity and between-class similarity inherent to RS scenes.…”

Section: Proposed Deep Metric Learning For Rsmentioning

confidence: 99%

Deep Metric Learning Based on Scalable Neighborhood Components for Remote Sensing Scene Characterization

Kang

Fernández-Beltrán

et al. 2020

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

With the development of convolutional neural networks (CNN), the semantic understanding of remote sensing scenes has been significantly improved based on their prominent feature encoding capabilities. Whereas many existing deep-learning models focus on designing different architectures, only few works in the remote sensing field have focused on investigating the performance of the learned feature embeddings and the associated metric space. In particular, two main loss functions have been exploited: the contrastive and the triplet loss. However, the straightforward application of these techniques to remote sensing images may not be optimal in order to capture their neighborhood structures in the metric space, due to the insufficient sampling of image pairs or triplets during the training stage, and to the inherent semantic complexity of remotely sensed data. To solve these problems, we propose a new deep metric learning approach, which overcomes the limitation on the class discrimination by means of two different components: 1) scalable neighborhood component analysis (SNCA), which aims at discovering the neighborhood structure in the metric space; and 2) the cross entropy loss, which aims at preserving the class discrimination capability based on the learned class prototypes. Moreover, in order to preserve feature consistency among all the mini-batches during training, a novel optimization mechanism based on momentum update is introduced for minimizing the proposed loss. An extensive experimental comparison (using several state-of-the-art models and two different benchmark datasets) has been conducted to validate the effectiveness of the proposed method from different perspectives, including: 1) classification; 2) clustering; and 3) image retrieval. The related codes of this paper will be made publicly available for reproducible research by the community.

show abstract

Section: Proposed Deep Metric Learning For Rsmentioning

confidence: 99%

Deep Metric Learning Based on Scalable Neighborhood Components for Remote Sensing Scene Characterization

Kang

Fernández-Beltrán

et al. 2020

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Next, the corresponding residual r T op i (y T op ) and r Conv i (y Conv ) are obtained by Eq. (7). Finally, the residuals are fused with weighting hyperparameters θ 1 and θ 2 .…”

Section: Feature Fusion and Sparse Representation Classificationmentioning

confidence: 99%

Remote Sensing Scene Classification Using Sparse Representation-Based Framework With Deep Feature Fusion

Mei

Yan

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Scene classification of high resolution remote sensing (RS) images has attracted increasing attentions due to its vital role in a wide range of applications. Convolutional Neural Networks (CNNs) have recently been applied on many computer vision tasks and have significantly boosted the performance including imagery scene classification, object detection and so on. However, classification performance heavily relies on the features that can accurately represent the scene of images, thus, how to fully explore the feature learning ability of CNNs is of crucial importance for scene classification. Another problem in CNNs is that it requires a large number of labeled samples, which is impractical in RS image processing. To address these problems, a novel sparse representation-based framework for small-samplesize RS scene classification with deep feature fusion is proposed. Specially, multi-level features are first extracted from different layers of CNNs to fully exploit the feature learning ability of CNNs. Note that the existing well-trained CNNs, e.g., AlexNet, VGGNet, and ResNet50, are used for feature extraction, in which no labeled samples is required. Then, sparse representation-based classification is designed to fuse the multi-level features, which is especially effective when only a small number of training samples are available. Experimental results over two benchmark datasets, e.g., UC-Merced and WHU-RS19, demonstrated that the proposed method can effectively fuse different levels of features learned in CNNs, and clearly outperform several state-of-the-art methods especially with limited training samples.

show abstract

“…This kind of methods divide the datasets into source domain and target domain, the former is different from latter but similar, the latter can obtain the tags through various transfer learning techniques, and is further used to train the scene classification model. Related works include Song et al [54], Bazi et al [55], Gong et al [56] and Li et al [57].…”

Section: Real Samplesmentioning

confidence: 99%

Generating and Sifting Pseudolabeled Samples for Improving the Performance of Remote Sensing Image Scene Classification

Qian

Chen

Yue

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Deep learning based remote sensing image scene classification methods are the current mainstream, and enough labeled samples are very important for their performance.Considering the fact that manual labeling of samples requires high labor and time cost, lots of methods have been proposed to automatically generate pseudo samples from real samples, however, existing methods can not directly sift the pseudo samples from the perspective of model training. To address this problem, a generating and sifting pseudo labeled samples scheme is proposed in this paper. First of all, the existing SinGAN is used to generate multiple groups of pseudo samples from the real samples. Afterwards, the proposed quantitative sifting measure which can evaluate both the authenticity and diversity from the perspective of model training is employed to select the best pseudo samples from the multiple generated pseudo samples. Finally, the selected pseudo samples and real samples are used to pretrain and finetune the deep scene classification network (DSCN) respectively. Moreover, the focal loss which is originally proposed for object detection is adopted to replace the traditional cross entropy loss in this paper. A designed quantitative evaluation shows that the value of proposed quantitative sifting measure is proportional to the overall accuracy, which validates the effectiveness of proposed quantitative sifting measure. The comprehensive quantitative comparisons on AID and NWPU-RESISC45 datasets in terms of overall accuracy and confusion matrices demonstrate that incorporating the pseudo samples selected by proposed sifting measure and the focal loss can improve the performance of DSCN.

show abstract

Domain Adaptation for Convolutional Neural Networks-Based Remote Sensing Scene Classification

Cited by 111 publications

References 12 publications

Deep Metric Learning Based on Scalable Neighborhood Components for Remote Sensing Scene Characterization

Deep Metric Learning Based on Scalable Neighborhood Components for Remote Sensing Scene Characterization

Remote Sensing Scene Classification Using Sparse Representation-Based Framework With Deep Feature Fusion

Generating and Sifting Pseudolabeled Samples for Improving the Performance of Remote Sensing Image Scene Classification

Contact Info

Product

Resources

About