目标检测——day56 Unmixing_Convolutional_Features_for_Crisp_Edge_Detection(用于清晰边缘探测的卷积特征分解)

Unmixing_Convolutional_Features_for_Crisp_Edge_Detection

  • 2 METHODOLOGY
    • 2.2 The Tracing Loss
      • 2.2.1 WeightedCross Entropy
      • 2.2.2 Feature Unmixing byTracing Boundaries
    • 2.3 Context-Aware Fusion Block
  • 3 EXPERIMENTS AND ANALYSIS
    • 3.1 Datasets

2 METHODOLOGY

2.2 The Tracing Loss

  • 模型训练过程中,LCE进行粗略的边缘学习,LBDRY通过特征分解进行边缘定位细化,LTEX对纹理区域进行较强的整体抑制。
  • 实现了清晰的边缘生成,比单加权交叉熵具有更小的定位模糊性

2.2.1 WeightedCross Entropy

式(1)

2.2.2 Feature Unmixing byTracing Boundaries

boundary tracing function:式(2)

texture suppression function:式(3)

2.3 Context-Aware Fusion Block

CoFusion的机制:如图3所示
Z:代表了 L 侧的边缘热图;
W_context:通过注意力模块从Z中学习得出的权重图。

  • 具体的说,从Z中提取出得分图 A_score ,通过 3 个 3 x 3 卷积层获取上下文信息用来推断 W_contextA_score 随后通过 Softmax 激活来规范化,以获得权重图 W_context
    P_final 通过下面两步进行计算:式(6)、(7)

3 EXPERIMENTS AND ANALYSIS

3.1 Datasets

  • BSDS500:challenging edge detection bench- mark
  • NYUDv2:challenging dataset for indoor scene pars- ing and is also a commonly used benchmark for edge detection evalu- ation
  • Multicue Dataset: This dataset strictly distinguishes the defi- nitions of boundary and edge, and it thus consists of two sub data- sets: Multicue Boundary and Multicue Edge

你可能感兴趣的:(CV,深度学习,计算机视觉,目标检测)