U²Mamba通过双层嵌套U结构提升显著目标检测精度。
U$^2$Mamba: A Two-level Nested U-structure Mamba for Salient Object Detection

- 设计多尺度Mamba U块,增强局部特征提取能力
- 采用分层监督训练,提升各层级特征表达
- 在多个数据集上超越现有方法,适合图像分割任务
基于Mamba的模型在显著目标检测(SOD)中展现出建模长序列的优势,但现有方法往往未能充分挖掘上下文信息和网络深度。本文提出U²Mamba,一种创新的U结构网络。引入多尺度Mamba U块(MMUBs)以增强模型深度,提升局部特征提取能力。设计嵌套式U结构,融合浅层与深层的多尺度感受野,有效获取更丰富的上下文信息与长距离依赖,且不受分辨率限制。摒弃传统深监督与顶层监督,提出分层训练监督机制,在每一层级计算损失。大量实验表明,U²Mamba在多个SOD基准测试中表现优异,性能优于当前主流方法。代码已开源:https://github.com/JL021/U2Mamba。
原文摘要 · Abstract (English)
Mamba-based models have emerged as a promising alternative for salient object detection (SOD), offering significant advantages in modeling long sequences. However, existing models often fail to explore contextual information and the depth of the entire architecture. This paper introduces U$^2$Mamba, a powerful and innovative U-structured network for salient object detection. We propose multiscale Mamba U-blocks (MMUBs) that enhance the model depth to improve local feature extraction capabilities. Our newly developed nested U-structure, incorporating MMUBs, enables the network to integrate various receptive fields from shallow and deep layers, thereby collecting richer contextual information and longer-range data without being constrained by resolution. Instead of using the traditional deep supervision scheme and top-level supervised training, we propose a hierarchical training supervision method where the loss is computed at each level during the training process. Extensive experiments demonstrate that U$^2$Mamba achieves highly competitive performance against state-of-the-art methods. The source code is available at \url{https://github.com/JL021/U2Mamba}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。