Abstract
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.
Similar content being viewed by others
References
Ren S, He K, Girshick R et al (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149. https://doi.org/10.1109/TPAMI.2016.2577031
Girshick R (2015) Fast R-CNN. In: IEEE international conference on computer vision, Santiago, pp 1440–1448. https://doi.org/10.1109/ICCV.2015.169
Shelhamer E, Long J, Darrell T (2017) Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 39(4):640–651. https://doi.org/10.1109/TPAMI.2016.2572683
Yu Z, Feng C, Liu M et al (2017) CASENet: deep category-aware semantic edge detection. In: IEEE conference on computer vision and pattern recognition, Honolulu, HI, pp 1761–1770. https://doi.org/10.1109/CVPR.2017.191
Guillemot C, Le Meur O (2014) Image inpainting : overview and recent advances. IEEE Signal Process Mag 31(1):127–144. https://doi.org/10.1109/MSP.2013.2273004
Wang Q, Han T, Qin Z et al (2020) Multitask attention network for lane detection and fitting. IEEE Trans Neural Netw Learn Syst PP(99):1–13. https://doi.org/10.1109/TNNLS.2020.3039675
Zhao Z, Wang Qi, Li X (2020) Deep reinforcement learning based lane detection and localization. Neurocomputing 413(6):328–338
Arbeláez P, Maire M, Fowlkes C, Malik J (2011) Contour detection and hierarchical image segmentation. IEEE Trans Pattern Anal Mach Intell 33(5):898–916. https://doi.org/10.1109/TPAMI.2010.161
Chen L, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2018) deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell 40(4):834–848. https://doi.org/10.1109/TPAMI.2017.2699184
Silberman N, Hoiem D, Kohli P, Fergus R. Indoor segmentation and support inference from RGBD images. In: 12th European conference on computer vision, vol 7576(5):746–760
Mely DA, Kim J, McGill M, Guo Y, Serre T (2016) A systematic comparison between visual cues for boundary detection. Vis Res 120:93–107. https://doi.org/10.1016/j.visres.2015.11.007
Li X, Shen H, Zhang L et al (2014) Recovering quantitative remote sensing products contaminated by thick clouds and shadows using multitemporal dictionary learning. IEEE Trans Geosci Remote Sens 52(11):7086–7098. https://doi.org/10.1109/TGRS.2014.2307354
Canny J (1986) A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell PAMI-8(6):679–698. https://doi.org/10.1109/TPAMI.1986.4767851
Fram JR, Deutsch ES (1975) On the quantitative evaluation of edge detection schemes and their comparison with human performance. IEEE Trans Comput C–24(6):616–628. https://doi.org/10.1109/T-C.1975.224274
Perona P, Malik J (1990) Scale-space and edge detection using anisotropic diffusion. IEEE Trans Pattern Anal Mach Intell 12(7):629–639. https://doi.org/10.1109/34.56205
Liu Y, Cheng M, Hu X, Wang K, Bai X (2017) Richer convolutional features for edge detection. In: 2017 IEEE conference on computer vision and pattern recognition, Honolulu, HI, pp 5872–5881. https://doi.org/10.1109/CVPR.2017.622
He J, Zhang S, Yang M et al (2019) Bi-directional cascade network for perceptual edge detection. In: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR), Long Beach, CA, USA, pp 3823–3832. https://doi.org/10.1109/CVPR.2019.00395
Shen W, Wang X, Wang Y, Bai X, Zhang Z (2015) DeepContour: a deep convolutional feature learned by positive-sharing loss for contour detection. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), Boston, MA, pp 3982–3991. https://doi.org/10.1109/CVPR.2015.7299024
Bertasius G, Shi J, Torresani L (2015) DeepEdge: a multi-scale bifurcated deep network for top-down contour detection. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), Boston, MA, pp 4380–4389. https://doi.org/10.1109/CVPR.2015.7299067
Xie S, Tu Z (2015) Holistically-nested edge detection. In: IEEE international conference on computer vision, Santiago, pp 1395–1403. https://doi.org/10.1109/ICCV.2015.164
Deng R, Shen C, Liu S, Wang H, Liu X (2018) Learning to predict crisp boundaries. Comput Vis ECCV. https://doi.org/10.1007/978-3-030-01231-1_35
He K, Zhang X, Ren S, et al. (2016) Identity mappings in deep residual networks. Preprint http://arxiv.org/abs/1603.05027
Szegedy C, Ioffe S, Vanhoucke V, et al. (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-First AAAI conference on artificial intelligence, San Francisco, pp 4278–4284
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. Preprint http://arxiv.org/abs/1409.1556
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, NV, pp 770–778. https://doi.org/10.1109/CVPR.2016.90
Wang Y, Zhao X, Huang K (2017) Deep crisp boundaries. In: 2017 IEEE conference on computer vision and pattern recognition, Honolulu, HI, pp 1724–1732. https://doi.org/10.1109/CVPR.2017.187
Funding
This work was supported by the Fundamental Research for the Central Universities of China under Grant E17JB00150.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wang, Y., Wang, L., Qiu, J. et al. Multi-residual Connection Network for Edge Detection. Neural Process Lett 53, 2165–2174 (2021). https://doi.org/10.1007/s11063-021-10503-z
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-021-10503-z