Search

The unique challenge in SAR object detection is the strong speckle noise inherent in SAR imagery. Existing learning-based works mainly focus on architectural enhancements, and fail to consider the valuable semantic information that can mitigate the effects of speckle noise. Large pretrained segment anything model (SAM) is a powerful foundational model with general semantic knowledge. However, SAM is not fully exploited for SAR object detection. This study paves the way for applying SAM for SAR object detection. Rather than fine-tuning the SAM network, we propose three mask-guided learning strategies by simply utilizing the semantic masks generated by SAM. Built upon the advanced RealTime DEtection TRansformer (RT-DETR) framework, the Semantic Assisted DETR, deemed as SA-DETR, integrates prior semantics from SAM into the SAR detection task. To be specific, first, we propose the mask-guided feature denoising module in the encoder stage, to enhance the network's discrimination of positives and negatives. Second, we propose the mask-guided query selection for initial query generation, which is beneficial for the decoder refinement. Finally, the mask-guided instance segmentation is proposed to achieve more accurate localization. To validate the superiority of the proposed SA-DETR, extensive experiments are conducted on two benchmark datasets, i.e., the SAR ship detection dataset (SSDD) and the recently published COCO-level large-scale multiclass SAR object detection dataset (SARDet-100K). Experimental results on both datasets outperform previous advanced detectors, achieving a new state-of-the-art with 99.0 $AP_{50}$ and 88.4 $mAP_{50}$ on SSDD and SARDet-100 K, respectively.

The acquisition of global context and boundary information is crucial for the semantic segmentation of remote sensing (RS) images. In contrast to convolutional neural networks (CNNs), transformers exhibit superior performance in global modeling and shape feature encoding, which provides a novel avenue for obtaining global context and boundary information. However, current methods fail to effectively leverage these distinctive advantages of transformers. To address this issue, we propose a novel single encoder and dual decoders architecture called STDSNet, which embeds the Swin transformer into the dual-stream network for semantic segmentation of RS imagery. The proposed STDSNet employs the Swin transformer as the network backbone in the encoder to address the limitations of CNNs in global modeling and encoding shape features. The dual decoder comprises two parallel streams, namely the global stream (GS) and the shape stream (SS). The GS utilizes the global context fusion module (GCFM) to address the loss of global context during upsampling. It further integrates GCFMs with skip connections and a multiscale fusion strategy to mitigate large-scale regional object classification errors resulting from similar features or shadow occlusion in RS images. The SS introduces the gate convolution module (GCM) to filter out irrelevant features, allowing it to focus on processing boundary information, which improves the semantic segmentation performance of small targets and their boundaries in RS images. Extensive experiments demonstrate that STDSNet outperforms other state-of-the-art methods on the ISPRS Vaihingen and Potsdam benchmarks.

Extreme bradycardia (EB), extreme tachycardia (ET), ventricular tachycardia (VT), and ventricular flutter (VF) are the four types of life-threatening arrhythmias, which are symptoms of cardiovascular diseases. Therefore, in this study, a method of life-threatening arrhythmia recognition is proposed based on pulse rate variability (PRV). First, noise and interference are wiped out from the arterial blood pressure (ABP), and the PRV signal is extracted. Then, 19 features are extracted from the PRV signal, and 15 features with highly important and significant variation were selected by random forest (RF). Finally, the back-propagation neural network (BPNN), extreme learning machine (ELM), and decision tree (DT) are used to build, train, and test classifiers to detect life-threatening arrhythmias. The experimental data are obtained from the MIMIC/Fantasia and the 2015 Physiology Net/CinC Challenge databases. The experimental results show that the DT classifier has the best average performance with accuracy and kappa coefficient (kappa) of 98.76 ± 0.08% and 97.59 ± 0.15%, which are higher than those of the BPNN (accuracy = 94.85 ± 1.33% and kappa = 89.95 ± 2.62%) and ELM (accuracy = 95.05 ± 0.14% and kappa = 90.28 ± 0.28%) classifiers. The proposed method shows better performance in identifying four life-threatening arrhythmias compared to existing methods and has potential to be used for home monitoring of patients with life-threatening arrhythmias.

With the development of Internet technology, social media platforms have become an indispensable part of people’s lives, and social media have been integrated into people’s life, study, and work. On various forums, such as Taobao and Weibo, a large number of people’s footprints are left all the time. It is these chats, comments, and other remarks with people’s emotional evaluations that make up part of public opinion. Analysis of this network public opinion is conducive to maintaining the peaceful development of society. Therefore, sentiment analysis has become a hot research field and has made great strides as one of the hot topics in the field of natural language processing. Currently, the BERT model and its variants have achieved excellent results in the field of NLP. However, these models cannot be widely used due to huge demands on computing resources. Therefore, this paper proposes a model based on the transformer mechanism, which mainly includes two parts: knowledge distillation and text augmentation. The former is mainly used to reduce the number of parameters of the model, reducing the computational cost and training time of the model, and the latter is mainly used to expand the task text so that the model can achieve excellent results in the few-sample sentiment analysis task. Experiments show that our model achieves competitive results.

Distance metric learning has achieved great success in person re‐identification. Most existing methods that learn metrics from pairwise constraints suffer the problem of imbalanced data. In this study, the authors present a large margin relative distance learning (LMRDL) method which learns the metric from triplet constraints, so that the problem of imbalanced sample pairs can be bypassed. Different from existing triplet‐based methods, LMRDL employs an improved triplet loss that enforces penalisation on the triplets with minimal inter‐class distance, and this leads to a more stringent constraint to guide the learning. To suppress the large variations of pedestrian's appearance in different camera views, the authors propose to learn the metric over the intra‐class subspace. The proposed method is formulated as a logistic metric learning problem with positive semi‐definite constraint, and the authors derive an efficient optimisation scheme to solve it based on the accelerated proximal gradient approach. Experimental results show that the proposed method achieves state‐of‐the‐art performance on three challenging datasets (VIPeR, PRID450S, and GRID).

Multi-baseline (MB) phase unwrapping (PU) is a key step of MB synthetic aperture radar (SAR) interferometry (InSAR). Compared with the traditional single-baseline (SB) PU, MB PU is applicable to the area where topography varies violently without obeying the phase continuity assumption. A two-stage programming MB PU approach (TSPA) proposed by H. Yu. builds the link between SB and MB PUs, so many existing classical SB PU methods can be transplanted into the MB domain. In this paper, an extended PU max-flow/min-cut (PUMA) algorithm for MB InSAR using the TSPA, referred to as TSPA-PUMA, is proposed, consisting of a two-stage programming procedure. In stage 1, phase gradients are estimated based on Chinese remainder theorem (CRT). In stage 2, a Markov random field (MRF) model of PUMA is designed for modeling local contextual dependence based on the phase gradients obtained by stage 1. Subsequently, the energy of the MRF model is minimized by graph cuts techniques. The experiment results illustrate that the TSPA-PUMA method can drastically enhance the accuracy of the original PUMA method in the rugged area, and is more efficient than the original TSPA method. In addition, the noise robustness of TSPA-PUMA can be improved through adding more interferograms with different baseline lengths.

One of the challenges in fine-grained classification is that subcategories with significant similarity are hard to be distinguished due to the equal treatment of all subcategories in existing algorithms. In order to solve this problem, a fine-grained image classification method by combining a bilinear convolutional neural network (B-CNN) and the measurement of subcategory similarities is proposed. Firstly, an improved weakly supervised localization method is designed to obtain the bounding box of the main object, which allows the model to eliminate the influence of background noise and obtain more accurate features. Then, sample features in the training set are computed by B-CNN so that the fuzzing similarity matrix for measuring interclass similarities can be obtained. To further improve classification accuracy, the loss function is designed by weighting triplet loss and softmax loss. Extensive experiments implemented on two benchmarks datasets, Stanford Cars-196 and Caltech-UCSD Birds-200-2011 (CUB-200-2011), show that the newly proposed method outperforms in accuracy several state-of-the-art weakly supervised classification models.