跳到正文
arXiv cs.AI· Guoping Xu, Jinling Zhu, Liuyue Li·· 4 小时前AI 评分26

LeViT-UNet++:兼顾细粒度细节与全局上下文的高效医学图像分割架构

LeViT-UNet++: Towards Balanced Fine-Grained Details and Context for Efficient Medical Image Segmentation

AI 导读

LeViT-UNet++ 提出一种高效编码器-解码器架构,通过 Haar Wavelet 多尺度下采样(HWMD)模块将特征分解为高低频分量,缓解下采样中的细节丢失,并用深度可分离卷积解码器融合 Transformer 全局表示与局部空间特征。

正文 · 原文

View PDF

Abstract:Efficient medical image segmentation is essential for clinical applications requiring fast and accurate delineation, such as surgical navigation, radiation therapy, and real-time image-guided intervention. Despite substantial advances in convolutional neural networks and Transformers, attaining high accuracy under limited computational resources remains difficult, because reducing model complexity often sacrifices fine-grained structural details and global context modeling, yielding an unfavorable accuracy-efficiency trade-off. To address this, we propose LeViT-UNet++, an efficient encoder-decoder architecture that better balances local detail preservation and global context modeling. Specifically, we introduce a Haar Wavelet Multi-Scale Downsampling (HWMD) module that decomposes feature representations into low- and high-frequency components to extract multi-scale structural information, thereby mitigating detail loss during downsampling. We further develop a depthwise convolution-based decoder that integrates multi-scale global representations from Transformer blocks with local spatial features, enabling progressive feature refinement while reducing computational overhead. Evaluated on four benchmarks (Synapse, ACDC, LA2018, and MSD Heart) under both 2D and 3D settings, LeViT-UNet++ achieves competitive accuracy with a compact parameter footprint and fast inference. On Synapse, for instance, it attains a DSC of 76.57% with only 8.025M parameters and 241.72 FPS, confirming a favorable accuracy-efficiency balance. These results demonstrate the effectiveness of combining wavelet-based multi-scale feature extraction with lightweight local-global feature fusion for efficient medical segmentation. The source code is available at this https URL.
Comments: 24 pages, 5 figure
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Multimedia (cs.MM)
Cite as: arXiv:2611.22482 [cs.CV]
  (or arXiv:2611.22482v1 [cs.CV] for this version)
  https://doi.org/10.48550/arXiv.2611.22482

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Guoping Xu [view email]
[v1] Tue, 17 Nov 2026 09:39:42 UTC (1,071 KB)

来源:arXiv cs.AI · arxiv.org