Registration of multi-modal remote sensing images with geometric distortions is one of the fundamental applications, but it remains difficult since multi-modal remote sensing images have significant differences in both radiometric and geometric features. One of the challenges is the disregarding of modality-specific information, which hinders the model from focusing on the content information of structure and texture due to differences in radiometric features. In this paper, an unsupervised Content-focused Hierarchical Alignment Network (CHA-Net) is proposed, which is constructed based on the theory of domain adaptation. The kernel idea of CHA-Net is to weaken the style differences among different modal images and achieve non-rigid multi-modal remote sensing image registration. CHA-Net is a hierarchical refinement model, where different scales of features are aligned respectively by utilizing the field calibration module and gradually generating the registration field. To be specific, CHA-Net consists of two structures: the Siamese Feature Decoupling (SFD) structure and the Hierarchical Refinement Alignment (HRA) structure. The SFD aims at reducing the style differences caused by cross-modal differences and developing a shared-weight Siamese network to map images to content feature space. The HRA enhances the ability of the network by capturing global distortions based on the Transformer model. Experiments on public datasets indicate that compared with other methods, CHA-Net performs better when geometric and radiometric distortions appear.

Air pollution and aging population have caused increasing rates of lung diseases and elderly lung diseases year by year. At the same time, the outbreak of COVID-19 has brought challenges to the medical system, which placed higher demands on preventing lung diseases and improving diagnostic efficiency to some extent. Artificial intelligence can alleviate the burden on the medical system by analyzing lung sound signals to help to diagnose lung diseases. The existing models for lung sound recognition have challenges in capturing the correlation between time and frequency information. It is difficult for convolutional neural network to capture multi-scale features across different resolutions, and the fusion of features ignores the difference of influences between time and frequency features. To address these issues, a lung sound recognition model based on multi-resolution interleaved net and time-frequency feature enhancement was proposed, which consisted of a heterogeneous dual-branch time-frequency feature extractor (TFFE), a time-frequency feature enhancement module based on branch attention (FEBA), and a fusion semantic classifier based on semantic mapping (FSC). TFFE independently extracts the time and frequency information of lung sounds through a multi-resolution interleaved net and Transformer, which maintains the correlation between time-frequency features. FEBA focuses on the differences in the influence of time and frequency information on prediction results by branch attention. The proposed model achieved an accuracy of 91.56% on the combined dataset, by an improvement of over 2.13% compared to other models.

Lung diseases are serious threats to human health and life, therefore, an accurate diagnosis of lung diseases is significant. The use of artificial intelligence to analyze lung sounds can aid in diagnosing lung diseases. Most of the existing lung sound recognition methods ignore the correlation between the time-domain and frequency-domain information of the lung sounds. Additionally, the spectrograms used in these models do not adequately capture the detailed features of the lung sounds. This paper proposes a model based on wavelet feature enhancement and time-frequency synchronous modeling, comprising a dual wavelet analysis module (DWAM), a cubic network, and an attention module. DWAM in the model performed a dual wavelet transformation on the spectrograms to extract the detailed features of the lung sounds. The cubic network comprised multiple cubic gated recursive units to capture the correlation of the time-frequency of the lung sounds using the time-frequency synchronous modeling. The attention module, which includes temporal and channel attention, was used to enhance the time-domain and channel dimension features. In the combined dataset and the International Conference on Biomedical and Health Informatics 2017 dataset, the suggested framework outperforms existing models by more than 1.36% and 4.28%, respectively.

Recently, feature pyramid has been widely exploited in remote sensing detectors, which greatly alleviates the problem arising from scale variation across objects in remote sensing images. However, these object detectors with feature pyramid give insufficient consideration that objects in remote sensing images usually maintain symmetrical shape. To address this issue, we propose an anchor-free-based detector called Centerness-Aware Network (CANet), which could capture the symmetrical shape of objects in remote sensing images. The kernel structure of CANet is a new Centerness-Aware Model (CAM) that contains three components: Multiscale Centerness Descriptor (MSCD), Centerness Detection Head (CDH), and Feature Selective Module (FSM). Considering that symmetrical objects will maintain a rigid appearance around their center region, three components are integrated into the feature pyramid to extract and utilize the features around the center region. More precisely, the MSCD is embedded into the feature pyramid and highlights the center of current objects through the attention mechanism. Guided by the MSCD, the CDH could accurately capture the center of objects by per-pixel prediction. Furthermore, the FSM is connected to the CDH, which guides the CDH to adaptively select the optimal feature level from the pyramidal features. The selected feature level could describe the best semantic information around the center region, which helps the network progressively fit the symmetrical shape of remote sensing objects. Besides, we also design the hybrid loss function to effectively train CAM in the end-to-end way. The experiments show that our network is competitive with some state-of-the-art detection networks.

It requires pixel-by-pixel annotations to obtain sufficient training data in supervised remote sensing image segmentation, which is a quite time-consuming process. In recent years, a series of domain-adaptation methods was developed for image semantic segmentation. In general, these methods are trained on the source domain and then validated on the target domain to avoid labeling new data repeatedly. However, most domain-adaptation algorithms only tried to align the source domain and the target domain in the pixel level or the representation level, while ignored their cooperation. In this letter, we propose an unsupervised domain-adaptation method by Joint Pixel and Representation level Network (JPRNet) alignment. The major novelty of the JPRNet is that it achieves joint domain adaptation in an end-to-end manner, so as to avoid the multisource problem in the remote sensing images. JPRNet is composed of two branches, each of which is a generative-adversarial network (GAN). In one branch, pixel-level domain adaptation is implemented by the style transfer with the Cycle GAN, which could transfer the source domain to a target domain. In the other branch, the representation-level domain adaptation is realized by adversarial learning between the transferred source-domain images and the target-domain images. The experimental results on the public data sets have indicated the effectiveness of the JPRNet.

Remote sensing image scene classification refers to assigning specific semantic labels for remote sensing images. Due to the lack of labeled remote sensing images, domain adaptation is applied to remote sensing image scene classification. However, recent proposed methods mainly focus on the closed set scenario. In this paper, we explore the open set scenario and introduce an open set domain adaptation network (OSDANet) for remote sensing image scene classification. Inspired by the idea of Generative Adversarial Network (GAN), we design a feature generator as well as a classifier which are learnt in an adversarial way. The purpose of the classifier is to find a boundary between the source and the target samples, while the feature generator attempts to force target samples away from the boundary. Especially, for the target samples, the feature generator will determine whether to align them with source samples or reject them as unknown target samples. The experimental results have indicated the effectiveness of the proposed method.