Scholarlink

<p>This paper explores using convolutional neural networks (CNNs) for unsupervised image segmentation. The method enhances pixel labeling accuracy through superpixel and propagates back strategies. Leveraging CNN’s feature extraction capabilities, pixels are assigned labels without training data or prior knowledge. In an unsupervised context, a single image is the network’s input, and parameters are updated via gradient descent. A preprocessing module applies image smoothing before network input to improve segmentation performance. The convolutional kernels alternate between <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="521_2025_11122_Article_IEq1.gif" Format="GIF" Height="14" Rendition="HTML" Resolution="72" Type="Linedraw" Width="39" /> </InlineMediaObject> <EquationSource Format="TEX">\(3\times 3\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mn>3</mn> <mo>×</mo> <mn>3</mn> </mrow> </math></EquationSource> </InlineEquation> and <InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="521_2025_11122_Article_IEq2.gif" Format="GIF" Height="14" Rendition="HTML" Resolution="72" Type="Linedraw" Width="39" /> </InlineMediaObject> <EquationSource Format="TEX">\(1\times 1\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mn>1</mn> <mo>×</mo> <mn>1</mn> </mrow> </math></EquationSource> </InlineEquation> sizes, and the activation functions, including ReLU and Batch Normalization, are reordered. Additionally, the Gray-Level Co-occurrence Matrix is integrated, and an adaptive superpixel method is introduced. Experimental results show significant improvements in Precision, Recall, and F1-score across corresponding datasets and superior performance in statistical indices like ARE, DH, AMI, and FMI.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Zero-shot image segmentation for scene objects based on the L0 gradient minimization and adaptive superpixel method

  • 期刊论文

  • 发表日期：

    2025年3月12日

查看全文
  • Hailong Yan,
  • Junjian Huang,
  • Mao Zheng,
  • Yijie Tang

摘要

This paper explores using convolutional neural networks (CNNs) for unsupervised image segmentation. The method enhances pixel labeling accuracy through superpixel and propagates back strategies. Leveraging CNN’s feature extraction capabilities, pixels are assigned labels without training data or prior knowledge. In an unsupervised context, a single image is the network’s input, and parameters are updated via gradient descent. A preprocessing module applies image smoothing before network input to improve segmentation performance. The convolutional kernels alternate between \(3\times 3\) 3 × 3 and \(1\times 1\) 1 × 1 sizes, and the activation functions, including ReLU and Batch Normalization, are reordered. Additionally, the Gray-Level Co-occurrence Matrix is integrated, and an adaptive superpixel method is introduced. Experimental results show significant improvements in Precision, Recall, and F1-score across corresponding datasets and superior performance in statistical indices like ARE, DH, AMI, and FMI.