Search results

Vision transformers (ViT) detectors excel in processing natural images. However, when processing remote sensing images (RSIs), ViT methods generally exhibit inferior accuracy compared to approaches based on convolutional neural networks (CNNs). Recently, researchers have proposed various structural optimization strategies to enhance the performance of ViT detectors, but the progress has been insignificant. We contend that the frequent scarcity of RSI samples is the primary cause of this problem, and model modifications alone cannot solve it.

To address this, we introduce a faster RCNN-based approach, termed QAGA-Net, which significantly enhances the performance of ViT detectors in RSI recognition. Initially, we propose a novel quantitative augmentation learning (QAL) strategy to address the sparse data distribution in RSIs. This strategy is integrated as the QAL module, a plug-and-play component active exclusively during the model’s training phase. Subsequently, we enhanced the feature pyramid network (FPN) by introducing two efficient modules: a global attention (GA) module to model long-range feature dependencies and enhance multi-scale information fusion, and an efficient pooling (EP) module to optimize the model’s capability to understand both high and low frequency information. Importantly, QAGA-Net has a compact model size and achieves a balance between computational efficiency and accuracy.

We verified the performance of QAGA-Net by using two different efficient ViT models as the detector’s backbone. Extensive experiments on the NWPU-10 and DIOR20 datasets demonstrate that QAGA-Net achieves superior accuracy compared to 23 other ViT or CNN methods in the literature. Specifically, QAGA-Net shows an increase in mAP by 2.1% or 2.6% on the challenging DIOR20 dataset when compared to the top-ranked CNN or ViT detectors, respectively.

This paper highlights the impact of sparse data distribution on ViT detection performance. To address this, we introduce a fundamentally data-driven approach: the QAL module. Additionally, we introduced two efficient modules to enhance the performance of FPN. More importantly, our strategy has the potential to collaborate with other ViT detectors, as the proposed method does not require any structural modifications to the ViT backbone.

The purpose of this study is to investigate the effect of electrical and thermal stresses on the void formation of the Sn3.0Ag0.5Cu (SAC305) lead-free ball grid array (BGA) solder joints and to propose a modified mean-time-to-failure (MTTF) equation when joints are subjected to coupling stress.

The samples of the BGA package were subjected to a migration test at different currents and temperatures. Voltage variation was recorded for analysis. Scanning electron microscope and electron back-scattered diffraction were applied to achieve the micromorphological observations. Additionally, the experimental and simulation results were combined to fit the modified model parameters.

Voids appeared at the corner of the cathode. The resistance of the daisy chain increased. Two stages of resistance variation were confirmed. The crystal lattice orientation rotated and became consistent and ordered. Electrical and thermal stresses had an impact on the void formation. As the current density and temperature increased, the void increased. The lifetime of the solder joint decreased as the electrical and thermal stresses increased. A modified MTTF model was proposed and its parameters were confirmed by theoretical derivation and test data fitting.

This study focuses on the effects of coupling stress on the void formation of the SAC305 BGA solder joint. The microstructure and macroscopic performance were studied to identify the effects of different stresses with the use of a variety of analytical methods. The modified MTTF model was constructed for application to SAC305 BGA solder joints. It was found suitable for larger current densities and larger influences of Joule heating and for the welding ball structure with current crowding.