CNN-based methods have improved the performance of edge detection in recent years. However, the edge map predicted by the neural network has a problem of thickness. We analyze that this is due to the training problem caused by the unbalanced distribution of edge and non-edge pixels. We propose to use residual connections to solve the class-imbalanced training problem in edge samples. Moreover, we introduce a new biased cross-entropy loss function to better train the edge detection network, which will adjust the weights according to the ratio of edges and non-edges pixels. Compared to other methods, our method predicts clearer and crisp edges. We set up multiple long and short residual connections in the network to establish various information propagation pathways. This makes the final prediction of our method not only with contour information but also have rich details. We evaluated our method on the BSDS500 and NYUD datasets and showed promising results.

近年来，基于CNN的方法提高了边缘检测的性能。然而，由神经网络预测的边缘图具有厚度问题。我们分析这是由于边缘和非边缘像素分布不平衡引起的训练问题。我们建议使用残差连接来解决边缘样本中的类不平衡训练问题。此外，我们引入了新的有偏交叉熵损失函数来更好地训练边缘检测网络，该网络将根据边缘和非边缘像素的比率来调整权重。与其他方法相比，我们的方法可预测更清晰和清晰的边缘。我们在网络中建立了多个长短残差连接，以建立各种信息传播路径。这不仅使我们对方法的最终预测不仅具有轮廓信息，而且还具有丰富的细节。我们在BSDS500和NYUD数据集上评估了我们的方法，并显示出令人鼓舞的结果。