XZXinyan Zhang

Xinyan Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xinyan Zhang has a total of 4 co-authors. Here are the top co-authors by number of shared publications:

  • Tianlong Deng

    College of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing 210037, China

    1 shared publication
  • Wenjie Wu

    College of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing 210037, China

    1 shared publication
  • Yanyi Liu

    College of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing 210037, China

    1 shared publication
  • Yin Wu

    College of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing 210037, China

    1 shared publication

Latest Publications

  • Open Access

    LDS-Net: A Lightweight Dual-Branch Network for Slender Tree Branch Segmentation in Complex Natural Scenes

    by Xinyan Zhang, Tianlong Deng, Yin Wu, Wenjie Wu, Yanyi Liu

    Accurate semantic segmentation of slender curvilinear structures, such as tree branches, in complex natural scenes remains challenging. The main difficulties arise from frequent occlusions, ambiguous boundaries, and limited edge computing resources. To address these issues, we propose LDS-Net, a lightweight dual-branch network designed for thin and continuous branch structures. The Detail-Aware Branch uses the Dynamic Snake Convolution (DSConv) to model irregular local geometry, while the Context-Aware Branch uses a Spatial Efficient Separable Pyramid module (SESP) to capture multi-scale context. To improve segmentation under occlusion and boundary ambiguity, we further integrate a Global Topology Transformer module (GTT) and a boundary guidance mechanism (BG). These features are fused via a Pixel-Wise Attention Fusion module (PAF) and optimized using a multi-head compound loss. Experiments on USTD and N-ABSD show that LDS-Net outperforms six representative networks. It also requires only 14.19 G FLOPs, a 24% reduction compared with PIDNet-s. These results suggest that LDS-Net has potential for future deployment on resource-constrained agricultural and ecological monitoring platforms.