As a more challenging domain adaptation setting, universal domain adaptation (UniDA) introduces category shift on top of domain shift, which needs to identify unknown category in the target domain and avoid misclassif...
详细信息
As a more challenging domain adaptation setting, universal domain adaptation (UniDA) introduces category shift on top of domain shift, which needs to identify unknown category in the target domain and avoid misclassifying target samples into source private *** this end, we propose a novel UniDA approach named Batch Singular value Polarization and Weighted Semantic Augmentation (BSP-WSA).Specifically, we adopt an adversarial classifier to identify the target unknown category and align feature distributions between the two ***, we propose to perform SVD on the classifier's outputs to maximize larger singular values while minimizing those smaller ones, which could prevent target samples from being wrongly assigned to source private *** better bridge the domain gap, we propose a weighted semantic augmentation approach for UniDA to generate data on common categories between the two *** experiments on three benchmarks demonstrate that BSP-WSA could outperform existing state-of-the-art UniDA approaches. Copyright 2024 by the author(s)
Substations in the power grids are vulnerable to cyber-attacks, and thus can lead to multiple line contingencies. However, previous studies mainly focus on the single-stage contingencies, lacking of exploring the prop...
详细信息
Detecting oriented targets in remote sensing images amidst complex and heterogeneous backgrounds remains a formidable challenge in the field of object *** frameworks for oriented detection modules are constrained by i...
详细信息
Detecting oriented targets in remote sensing images amidst complex and heterogeneous backgrounds remains a formidable challenge in the field of object *** frameworks for oriented detection modules are constrained by intrinsic limitations,including excessive computational and memory overheads,discrepancies between predefined anchors and ground truth bounding boxes,intricate training processes,and feature alignment *** overcome these challenges,we present ASL-OOD(Angle-based SIOU Loss for Oriented Object Detection),a novel,efficient,and robust one-stage framework tailored for oriented object *** ASL-OOD framework comprises three core components:the Transformer-based Backbone(TB),the Transformer-based Neck(TN),and the Angle-SIOU(Scylla Intersection over Union)based Decoupled Head(ASDH).By leveraging the Swin Transformer,the TB and TN modules offer several key advantages,such as the capacity to model long-range dependencies,preserve high-resolution feature representations,seamlessly integrate multi-scale features,and enhance parameter *** improvements empower the model to accurately detect objects across varying *** ASDH module further enhances detection performance by incorporating angle-aware optimization based on SIOU,ensuring precise angular consistency and bounding box *** approach effectively harmonizes shape loss and distance loss during the optimization process,thereby significantly boosting detection *** evaluations and ablation studies on standard benchmark datasets such as DOTA with an mAP(mean Average Precision)of 80.16 percent,HRSC2016 with an mAP of 91.07 percent,MAR20 with an mAP of 85.45 percent,and UAVDT with an mAP of 39.7 percent demonstrate the clear superiority of ASL-OOD over state-of-the-art oriented object detection *** findings underscore the model’s efficacy as an advanced solution for challenging remote sensing object detection tasks.
With the rapid development of online platforms and the explosive growth of user-generated data, personalized recommendation systems have become increasingly crucial in delivering relevant content to users. Traditional...
详细信息
While deep learning techniques have shown promising performance in the Major Depressive Disorder (MDD) detection task, they still face limitations in real-world scenarios. Specifically, given the data scarcity, some e...
详细信息
Source code is an intermediary through which humans communicate with computer systems. It contains a large amount of domain knowledge which can be learned by statistical models. Furthermore, this knowledge can be used...
详细信息
As a material with good biocompatibility,hydroxyapatite(HAP)can have optical properties after doping with various rare earth *** a biocompatible fluorescent material,doped HAP could have broad applications in biologic...
详细信息
As a material with good biocompatibility,hydroxyapatite(HAP)can have optical properties after doping with various rare earth *** a biocompatible fluorescent material,doped HAP could have broad applications in biological probes,drug delivery,optoelectronic materials,fluorescence anti-counterfeiting,and other *** this paper,we put forward the preparation of HAP doped with terbium(Ⅲ)ions(Tb^(3+))by hydrothermal *** controlling the Tb^(3+)doping content in reaction and the reaction time,the changes in HAP's structure,morphology,and luminescence properties under different conditions were *** the doping amount of Tb^(3+)reached an optimal value,the dipole-quadrupole would occur and the concentration would be *** control experiment showed that the optimal Tb3+content was 7.5×10^(-5)mol,which showed the best fluorescence ***,a non-luminous material,was rarely used in the field of fluorescent anti-counterfeiting and photoelectric *** proposed to prepare a luminescent aramid/polyphenylene sulfide(ACFs/PPS)fiber paper and a new light-emitting diode(LED)using the Tb-doped HAP *** composite sample exhibited an excellent stability and fluorescence performance,which also demonstrated a possibility of HAP applications in anticounterfeiting and *** introduction of Tb3+dopant HAP was done to give HAP optical properties and broaden the application range of HAP.
In the environment of smart examination rooms, it is important to quickly and accurately detect abnormal behavior(human standing) for the construction of a smart campus. Based on deep learning, we propose an intellige...
详细信息
In the environment of smart examination rooms, it is important to quickly and accurately detect abnormal behavior(human standing) for the construction of a smart campus. Based on deep learning, we propose an intelligentstanding human detection (ISHD) method based on an improved single shot multibox detector to detect thetarget of standing human posture in the scene frame of exam room video surveillance at a specific examinationstage. ISHD combines the MobileNet network in a single shot multibox detector network, improves the posturefeature extractor of a standing person, merges prior knowledge, and introduces transfer learning in the trainingstrategy, which greatly reduces the computation amount, improves the detection accuracy, and reduces the trainingdifficulty. The experiment proves that the model proposed in this paper has a better detection ability for the smalland medium-sized standing human body posture in video test scenes on the EMV-2 dataset.
Infrared and visible image fusion (IVIF) aims to generate fused images with prominent targets and rich scene information. However, in low-light conditions, visible images lose accurate texture and color, reducing thei...
详细信息
This paper presents high quality YBa_(2)Cu_(3)O_(7-δ)(YBCO)thin films on LaAlO_(3)substrate for microwave devices prepared by pulsed laser deposition(PLD).The double-sided YBCO films cover a large area and have been ...
详细信息
This paper presents high quality YBa_(2)Cu_(3)O_(7-δ)(YBCO)thin films on LaAlO_(3)substrate for microwave devices prepared by pulsed laser deposition(PLD).The double-sided YBCO films cover a large area and have been optimized for key parameters relevant to microwave device applications,such as surface morphology and surface resistance(R_(s)).This was achieved by improving the target quality and increasing the oxygen pressure during deposition,*** evaluate the suitability of the YBCO films for microwave devices,a pair of microwave filters based on microstrip fabricated on films from this work and a commercial company were *** results show that the YBCO films in this work could completely meet the requirements for microwave devices.
暂无评论