We use cookies to improve your experience with our site.

基于局部对比度学习的精细边缘提取

Learning Local Contrast for Crisp Edge Detection

  • 摘要:
    研究背景 随着深度学习技术的进步,边缘提取算法的准确性得到了显著的提升,对图像语义结构的把握也更为到位。但深度神经网络所预测的边缘分布是较为粗粒度的结果,在实际使用中需要经过一系列后处理加以优化,降低了深度学习算法的实用性。
    目的 使用深度神经网络直接端到端地预测细粒度的边缘分布。
    方法 本文提出了局部对比度学习的策略。采用局部对比度损失替换了传统边缘提取模型中使用的交叉熵损失,使用随机对比度方向优化的策略实现了高效的模型训练,取消旁路输出的约束改进网络输出的精细程度。
    结果 在BSDS和NYUD两个数据集上验证了新方法生成的边缘精细程度更高,同时在标准的带后处理评测流程下准确率与已有方法仍然持平。
    结论 本文论证了基于局部对比度的建模比传统的逐像素分类建模更适用于预测边缘这样一类细粒度的结构,这一方法可能也有助于改进其他对精细程度要求较高的图像理解和生成模型。

     

    Abstract: In recent years, the accuracy of edge detection on several benchmarks has been significantly improved by deep learning based methods. However, the prediction of deep neural networks is usually blurry and needs further post-processing including non-maximum suppression and morphological thinning. In this paper, we demonstrate that the blurry effect arises from the binary cross-entropy loss, and crisp edges could be obtained directly from deep convolutional neural networks. We propose to learn edge maps as the representation of local contrast with a novel local contrast loss. The local contrast is optimized in a stochastic way to focus on specific edge directions. Experiments show that the edge detection network trained with local contrast loss achieves a high accuracy comparable to previous methods and dramatically improves the crispness. We also present several applications of the crisp edges, including image completion, image retrieval, sketch generation, and video stylization.

     

/

返回文章
返回