SearcharxivSearch

arXiv subjects

Xiangyu Deng

Publications and source records attributed to Xiangyu Deng.

2 recordsLinked to original sources

Dark sector radiation corrections to invisible dark photon production: beyond fixed order

In this work we study invisible dark photon production at electron-positron colliders in a dark Abelian Higgs model at NLO (next-to-leading-order), and the physical distribution of squared missing mass $M_X^2$. We show that the fixed order correction to the total cross section for the process $e^+e^-\to \gamma A'$, with $A'$ the dark photon, is infrared-safe, but the corresponding differential distribution of $M_X^2$ reveals a quasi-collinear $1/M_X^2$ divergence when the masses of dark sector particles are much smaller than the hard scale. By using the Sudakov resummation method, we obtain an integrable, normalized distribution of $M_X^2$, which is actually the ``jet mass'' of the dark photon branch. We also discuss how these dark sector corrections impact the invisible dark photon search at electron-positron colliders.

hep-ph

MDFI-Net: Multiscale Differential Feature Interaction Network for Accurate Retinal Vessel Segmentation

The accurate segmentation of retinal vessels in fundus images is a great challenge in medical image segmentation tasks due to their highly complex structure from other organs.Currently, deep-learning based methods for retinal cessel segmentation achieved suboptimal outcoms,since vessels with indistinct features are prone to being overlooked in deeper layers of the network. Additionally, the abundance of redundant information in the background poses significant interference to feature extraction, thus increasing the segmentation difficulty. To address this issue, this paper proposes a feature-enhanced interaction network based on DPCN, named MDFI-Net.Specifically, we design a feature enhancement structure, the Deformable-convolutional Pulse Coupling Network (DPCN), to provide an enhanced feature iteration sequence to the segmentation network in a simple and efficient manner. Subsequently, these features will interact within the segmentation network.Extensive experiments were conducted on publicly available retinal vessel segmentation datasets to validate the effectiveness of our network structure. Experimental results of our algorithm show that the detection accuracy of the retinal blood vessel achieves 97.91%, 97.97% and 98.16% across all datasets. Finally, plentiful experimental results also prove that the proposed MDFI-Net achieves segmentation performance superior to state-of-the-art methods on public datasets.

cs.CV