Search

Synthetic aperture radar (SAR) ship detection and classification has gained unprecedented attention due to its important role in maritime transportation. Many deep learning-based detectors and classifiers have been successfully applied and achieved great progress. However, ships in SAR images present discrete and multi-centric features, and their scattering characteristics and edge information are sensitive to variations in target attitude angles (TAAs). These factors pose challenges for existing methods to obtain satisfactory results. To address these challenges, a novel target attitude angle-guided network (TAG-Net) is proposed in this article. The core idea of TAG-Net is to leverage TAA information as guidance and use an adaptive feature-level fusion strategy to dynamically learn more representative features that can handle the target imaging diversity caused by TAA. This is achieved through a TAA-aware feature modulation (TAFM) module. It uses the TAA information and foreground information as prior knowledge and establishes the relationship between the ship scattering characteristics and TAA information. This enables a reduction in the intra-class variability and highlights ship targets. Additionally, considering the different requirements of the detection and classification tasks for the scattering information, we propose a layer-wise attention-based task decoupling detection head (LATD). Unlike general deep learning methods that use shared features for both detection and classification tasks, LATD extracts multi-level features and uses layer attention to achieve feature decoupling and select the most suitable features for each task. Finally, we introduce a novel salient-enhanced feature balance module (SFB) to provide richer semantic information and capture the global context to highlight ships in complex scenes, effectively reducing the impact of background noise. A large-scale ship detection dataset (LSSDD+) is used to verify the effectiveness of TAG-Net, and our method achieves state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Range sidelobe is very common in synthetic aperture radar (SAR) images, particularly when imaging scene includes strongly scattering targets such as ships or complex buildings. As a kind of interference, it may reduce the image quality and hinder the image interpretation. Hence, range sidelobe suppression is an important mission for SAR images. The main task of mitigating the sidelobe is how to achieve the most effective suppression with the minimal resolution loss and signal-to-noise ratio (SNR) loss. However, the widely recognized classic method, spatially variant apodization (SVA), still has a lot of residual sidelobe energy and other problems. This article proposes a novel suppression approach based on time-variant transmission of chaotic frequency modulation (CFM) signals. The key is to build an appropriate transmitted signal set, where the signals are generated by various chaotic initial states and the same special map with low mixing rate and uniform invariant probability density (IPD). Due to their beneficial autocorrelation properties, the proposed approach achieves superior performance in range sidelobe suppression and resolution preservation. More importantly, it maintains the energy of the signals and overcomes the SNR loss that occurs in some classic methods, such as spectral weighting (SW) and SVA. In addition, it is suitable for both vertical and squint side-looking mode and can well reconstruct the weakly scattering targets which are severely disturbed by range sidelobe. All of them are validated by comparative experiments. [ABSTRACT FROM AUTHOR]

Azimuth ambiguity may introduce false targets into synthetic aperture radar images, particularly likely in inshore and oceanic observation. To suppress the azimuth ambiguities for any acquisition mode, a new model is developed to describe the impact of spatially variant azimuth antenna pattern weighting on azimuth ambiguities. By accurately estimating the ratio of ambiguous to main zone energy based on the model, the proposed algorithm selects the subspectra with less ambiguous disturbance, and adopts extrapolation with weighted energy measure to obtain a full spectrum. Due to spectral selection and extrapolation, the novel algorithm achieves superior performance in azimuth ambiguity suppression and resolution preservation, which is compared with the classical algorithm, and validated by applying TerraSAR-X and RADARSAT-2 images. [ABSTRACT FROM AUTHOR]

The resolution degradation poses a huge challenge for object detection (OD) in aerial imagery. The existing methods use super-resolution (SR) based on generative adversarial network (GAN) to restore texture details in degraded images. However, constrained detection results are still acquired due to object feature difference between restored and clear images. Therefore, we propose a simple yet effective learning method called mutual-feed learning (MFL) to solve the problem in this article. A closed-loop structure is designed via building the feedback connection based on the feedforward connection between the two tasks. It effectively delivers the object spatial and feature information from OD to SR and provides restoration-enhanced images from SR to OD. Specifically, a feedback of region of interest (FROI) module is introduced to realize a region-level discrimination under the guidance of object information. It guides the discrimination process of SR. Furthermore, a multiscale object information (MSOI) module is developed to implement a feature-level restoration by narrowing the differences in object-related features. It improves the generation process of SR. Then OD can be performed in restoration-enhanced images to obtain more accurate results. Extensive experiments over Northwestern Polytechnical University (NWPU) Very High Resolution (VHR)-10, Cars Overhead With Context (COWC), and Fine-grained Object Recognition (FAIR)1M datasets show that the method can achieve state-of-the-art results. [ABSTRACT FROM AUTHOR]

Boundary information is essential for the semantic segmentation of remote sensing images. However, most existing methods were designed to establish strong contextual information while losing detailed information, making it challenging to extract and recover boundaries accurately. In this article, a boundary-sensitive network (BSNet) is proposed to address this problem via dynamic hybrid gradient convolution (DHGC) and coordinate sensitive attention (CSA). Specifically, in the feature extraction stage, we propose DHGC to replace vanilla convolution (VC), which adaptively aggregates one VC kernel and two gradient convolution kernels (GCKs) into a new operator to enhance boundary information extraction. The GCKs are proposed to explicitly encode boundary information, which is inspired by traditional Sobel operators. In the feature recovery stage, the CSA is introduced. This module is used to reconstruct the sharp and detailed segmentation results by adaptively modeling the boundary information and long-range dependencies in the low-level features as the assistance of high-level features. Note that DHGC and CSA are plug-and-play modules. We evaluate the proposed BSNet on three public datasets: the ISPRS 2-D semantic labeling Vaihingen, the Potsdam benchmark, and the iSAID dataset. The experimental results indicate that BSNet is a highly effective architecture that produces sharper predictions around object boundaries and significantly improves the segmentation accuracy. Our method demonstrates superior performance on the Vaihingen, the Potsdam benchmark, and the iSAID dataset in terms of the mean $F_{1}$ , with improvements of 4.6%, 2.3%, and 2.4% over strong baselines, respectively. The code and models will be made publicly available. [ABSTRACT FROM AUTHOR]

Current unsupervised domain adaptation (UDA) techniques in semantic segmentation effectively decrease the domain discrepancy between the labeled source domain and unlabeled target domain, thereby enhancing the model's pixel-wise discriminative capability for target domain data. However, in remote sensing images (RSIs), our study uncovers that these approaches perform poorly in the presence of class distribution inconsistencies between the source and target domains. In this work, we propose a one-stage mean teacher framework with a novel auxiliary prototype classifier, named MTA, to address this issue. Specifically, the teacher model assigns pseudo labels at pixel level for target samples and captures knowledge from the student model via exponential moving average (EMA). With labeled source samples and target samples that have pseudo labels, the student model can alleviate the divergence between the source and target domains. In addition, the auxiliary prototype classifier (APC) reduces the performance degradation in the parametric softmax classifier of the student model caused by class distribution divergence. We also propose a prototype computation scheme to obtain each class prototype in the APC. Specifically, we build a memory bank for each class of the two domains to store feature embeddings dynamically. Then, we compute the class prototype by applying the clustering algorithm on memory banks corresponding to the class. Meanwhile, the APC reduces the intra-class domain discrepancy by optimizing the cross-entropy loss, which brings each class feature distribution of the two domains closer to the class prototype. The experimental results on RSIs UDA semantic segmentation tasks show the superiority of our approach over comparative methods. [ABSTRACT FROM AUTHOR]

Depression is a serious public health problem and an important factor leading to disease-related disability. Influenced by many factors, such as psychological, hormonal, and genetic factors, the incidence rate of depression in females is approximately two times that in males. However, in preclinical neuroscience research, the selection of the animals' sex for use in depression models has been controversial. At present, in most preclinical studies, the animals generally chosen in depression models have been male rodents rather than female rodents. It remains doubtful whether the data obtained from male animals can be generalized to female animals. The performance of female animals in preclinical studies of depression has been inconclusive. Based on a review of a large number of original studies in the PubMed database, it was found that although male rodents are more commonly used in the study of depression, the use of female animals also shows good modeling of depression and has its advantages. The influence of the animals' sex in the chronic unpredictable mild stress (CUMS) model needs further research. [ABSTRACT FROM AUTHOR]

Lightweight object detector is currently gaining more and more popularity in remote sensing. In general, it is hard for lightweight detectors to achieve competitive performance compared with the traditional deep models, while knowledge distillation (KD) is a promising training method to tackle the issue. Since the background is more complicated and the object size varies extremely in remote sensing images, it will deliver lots of noise and affect the training performance when directly applying the existing KD methods. To tackle the above problems, we propose an adaptive reinforcement supervision distillation (ARSD) framework to promote the detection capability of the lightweight model. First, we put forward a multiscale core features imitation (MCFI) module for transferring the knowledge of features, which can adaptively select the multiscale core features of objects for distillation and focus more on the features of small objects by an area-weighted strategy. In addition, a strict supervision regression distillation (SSRD) module is designed to select the optimal regression results for distillation, which facilitates the student to effectively imitate the more precise regression output of the teacher network. Massive experiments on a large-scale Dataset for Object deTection in Aerial images (DOTA), object DetectIon in Optical Remote sensing images (DIOR), and Northwestern Polytechnical University Very-High-Resolution 10-class (NWPU VHR) datasets prove that ARSD outperforms the existing distillation state-of-the-art (SOTA) methods. Moreover, the performance of the lightweight model trained with our method transcends other classic heavy and lightweight detectors, which beneficiates the development of lightweight models. [ABSTRACT FROM AUTHOR]

Despite tremendous success of molecular targeted therapy together with immunotherapy, only a small subset of patients can benefit from them. Chemotherapy remains the mainstay treatment for most of tumors including non-small cell lung cancer (NSCLC); however, non-selective adverse effects on healthy tissues and secondary resistance are the main obstacles. Meanwhile, the quiescent or dormant cancer stem-like cells (CSLCs) are resistant to antimitotic chemoradiotherapy. Complete remission can only be realized when both proliferative cancer cells and quiescent cancer stem cells are targeted. In the present research, we constructed a cooperatively combating conjugate (DTX-P7) composed of docetaxel (DTX) and a heptapeptide (P7), which specifically binds to cell surface Hsp90, and assessed the anti-tumor effects of DTX-P7 on non-small cell lung cancer. DTX-P7 preferentially suppressed tumor growth compared with DTX in vivo with a favorable distribution to tumor tissues and long circulation half-life. Furthermore, we revealed a distinctive mechanism whereby DTX-P7 induced unfolded protein response and eventually promoted apoptosis. More importantly, we found that DTX-P7 promoted cell cycle reentry of slow-proliferating CSLCs and subsequently killed them, exhibiting a "proliferate to kill" pattern. Collecitvely, by force of active targeting delivery of DTX via membrane-bound Hsp90, DTX-P7 induces unfolded protein response and subsequent apoptosis by degrading Hsp90, meanwhile awakens and kills the dormant cancer stem cells. Thus, DTX-P7 deserves further development as a promising anticancer therapeutic for treatment of various membrane-harboring Hsp90 cancer types. [ABSTRACT FROM AUTHOR]

ANNAO tablets derive from Chinese classical prescriptions of Angong Niuhuang Pills with modified compositions, which have been singly or combined used for stoke associated neurological disorders. However the underlying mechanism is not yet well-defined, the present study investigated its anti-ischemic effects in rat middle cerebral artery occlusion (MCAO) model and focused on mitochondrial quality control. Rats were subjected to 2 h of brain ischemia followed by 1 day or up to 7 days of reperfusion. Vehicle, ANNAO tablets or Edaravone were given at 1h after the start of reperfusion for 1 day or successive 7 days in MCAO rats. For the behavior assessment, Longa test and modified Neurological Severity Scores (m NSS) test were performed. Following the behavioral assessment, we assessed the protein expressions related to mitochondrial function. Moreover, we also assessed the neuroprotective effects of ANNAO tablets by immunohistochemical analysis. Compared with sham rats, ANNAO tablets improved the behavioral performance and decreased the infarction volume in the MCAO rats. Western blotting results showed that ANNAO tablets altered the expression level of multiple proteins related to mitochondrial function, elevated the ratio of Bcl-2/Bax and inhibited the apoptosis. Additionally, ANNAO tablets increased the number of NeuN positive neurons. The obtained data demonstrated that ANNAO tablets exhibited an obvious anti-cerebral ischemia-reperfusion effect, which could be attributed to the improvement of mitochondrial quality control. Image 1 [ABSTRACT FROM AUTHOR]