Abstract
Although deep convolutional neutral networks (CNNs) have significantly enhanced performance in image edge detection (ED), current models remain highly dependent on post-processing techniques such as non-maximum suppression (NMS), and often fail to deliver satisfactory perceptual results, while the performance will deteriorate significantly if the allowed error toleration distance decreases. These limitations arise from the uniform fusion of features across all pixels, regardless of their specific characteristics, such as the distinction between textural and edge areas. If the features extracted by the ED models are selected more meticulously and encompass greater diversity, the resulting predictions are expected to be more accurate and perceptually meaningful. Motivated by this observation, this paper proposes a novel feature selection paradigm for deep networks that facilitates the differential selection of features and can be seamlessly integrated into existing ED models. By incorporating this additional structure, the performance of conventional ED models is substantially enhanced without post-processing, while simultaneously enhancing the perceptual quality of the predictions. Extensive experimental evaluations validate the effectiveness of the proposed model.
Abstract (translated)
尽管深度卷积神经网络（CNN）在图像边缘检测（ED）方面显著提升了性能，但目前的模型仍然高度依赖于非极大值抑制（NMS）等后处理技术，并且常常无法提供令人满意的感知结果。如果允许的误差容忍距离减小，其性能会明显下降。这些限制源于对所有像素特征进行统一融合，而没有考虑到它们的具体特性，例如纹理区域和边缘区域之间的区别。如果通过ED模型提取的特征被更精心地选择并包含更大的多样性，则预测的结果有望更加准确且具有感知意义。 受此观察结果启发，本文提出了一种新颖的深度网络特征选择范式，该范式可以实现差异化特征的选择，并能够无缝集成到现有的边缘检测模型中。通过引入这种额外的结构，在不进行后处理的情况下显著提升了传统ED模型的性能，并同时提高了预测的质量感知度。广泛的实验评估验证了所提出的模型的有效性。
URL
https://arxiv.org/abs/2501.02534
