Richer Convolutional Features for Edge Detection

Yun Liu1      Ming-Ming Cheng1      Xiaowei Hu1      Kai Wang1      Xiang Bai2

1Nankai University     2HUST


In this paper, we propose an accurate edge detector using richer convolutional features (RCF). Since objects in natural images possess various scales and aspect ratios, learning the rich hierarchical representations is very critical for edge detection. CNNs have been proved to be effective for this task. In addition, the convolutional features in CNNs gradually become coarser with the increase of the receptive fields. According to these observations, we attempt to adopt richer convolutional features in such a challenging vision task. The proposed network fully exploits multiscale and multilevel information of objects to perform the image-to-image prediction by combining all the meaningful convolutional features in a holistic manner. Using VGG16 network, we achieve state-of-the-art performance on several available datasets. When evaluating on the well-known BSDS500 benchmark, we achieve ODS F-measure of 0.811 while retaining a fast speed (8 FPS). Besides, our fast version of RCF achieves ODS F-measure of 0.806 with 30 FPS.



We build a simple network based on VGG16 to produce side outputs of conv3_1, conv3_2, conv3_3, conv4_1, conv4_2 and conv4_3. One can clearly see that convolutional features become coarser gradually, and the intermediate layers conv3_1, conv3_2, conv4_1, and conv4_2 contain lots of useful fine details that do not appear in other layers.


Our RCF network architecture. The input is an image with arbitrary sizes, and our network outputs an edge possibility map in the same size. We combine hierarchical features from all the conv layers into a holistic framework, in which all of the parameters are learned automatically. Since receptive field sizes of conv layers in VGG16 are different from each other, our network can learn multiscale, including low-level and objectlevel, information that is helpful to edge detection.

The pipeline of our multiscale algorithm. The original image is resized to construct an image pyramid. And these multiscale images are input to RCF network for a forward pass. Then, we use bilinear interpolation to restore resulting edge response maps to original sizes. A simple average of these edge maps will output high-quality edges.

Evaluation on BSDS500 dataset

The evaluation results on standard BSDS500 dataset. Both single-scale and multiscale versions of RCF achieve better performance than humans.


The comparison with some competitors on BSDS500 dataset. The top three results are highlighted in red, green and blue respectively.


13 评论 在 "Richer Convolutional Features for Edge Detection"


您好!我使用RCF-singlescale.ipynb 在BSDS500上进行了简单的测试,速度只有12fps,测试代码中也没有生成F-measure性能指标的代码,这个性能指标是怎么得到的?谢谢!

Yun Liu
Yun Liu

我也不清楚您为什么测的速度只有12fps,可能是显卡或机器不同吧。RCF-singlescale.ipynb可以生成Edge的图像,然后您运行edge_nms.m进行NMS,edge_nms.m依赖于Piotr Dollar的Matlab toobox (。最后,请您用标准的BSDS500 Benchmark进行评测 (,生成F-measure等性能指标。