DeepEdge: A multi-scale bifurcated deep network for top-down contour detection

By Gedas Bertasius, Jianbo Shi, Lorenzo Torresani. 2014

524 citations recorded by the source corpus.

Contour detection has been a fundamental component in many image segmentation and object detection systems. Most previous work utilizes low-level features such as texture or saliency to detect contours and then use them as cues for a higher-level task such as object detection. However, we claim that recognizing objects and predicting contours are two mutually related tasks. Contrary to traditional approaches, we show that we can invert the commonly established pipeline: instead of detecting contours with low-level cues for a higher-level recognition task, we exploit object-related features as high-level cues for contour detection.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

InstanceCut: From Edges to Instances with MultiCut (2016, background): “Recent advances in deep learning have made this class of methods especially efﬁcient, since they automatically obtain rich feature representation for classiﬁcation [19, 29, 46, 6, 7, 51, 8].”
EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning (2019, background): “There is a large body of literature that addresses “Image-to-Edges” problems [5, 10, 26, 29].”
EDTER: Edge Detection with Transformer (2022, methodology): “Recently, convolutional neural networks (CNNs) have been successfully introduced the edge detection study [3, 4, 11, 12, 26, 29, 40, 46, 48, 52, 66].”
Holistically-Nested Edge Detection (2015, methodology): “This is significantly more efficient than existing CNN-basedmethods (Shen et al. 2015; Bertasius et al. 2015).”
Learning Representations for Automatic Colorization (2016, methodology): “Motivating this strategy is the success of similar architectures for semantic segmentation [4,10,14,23,27] and edge detection [1,11,25,34,43].”
Stacked Hourglass Networks for Human Pose Estimation (2016, background): “Our work is closely connected to fully convolutional networks [23] and other designs that process spatial information in multiple scales for dense prediction [15,30,31,32,33,34,35,36,37,38].”
UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory (2016, background): “We compare our method to some of the best-established methods of boundary detection [1, 23], as well as more recent, deep learning-based ones [6,28,41,48,49,90,107].”
Harmonic Networks: Deep Translation and Rotation Equivariance (2016, neutral): “759 DeepEdge†, [2] 0.”
Pushing the Boundaries of Boundary Detection using Deep Learning (2015, background): “Method ODS OIS AP gPb-owt-ucm (Arbelaez et al., 2011) 0.726 0.757 0.696 SE-Var (Doll´ar & Zitnick, 2015) 0.746 0.767 0.803 DeepNets (Kivinen et al., 2014) 0.738 0.759 0.758 N4-Fields (Ganin & Lempitsky, 2014) 0.753 0.769 0.784 DeepEdge (Bertasius et al., 2015) 0.753 0.772 0.807 CSCNN (Hwang & Liu, 2”
DenseBox: Unifying Landmark Localization with End to End Object Detection (2015, background): “Recent works[2, 22] indicate that using features from different convolution layers can enhance performance in task such as edge detection and segmentation.”
High-for-Low and Low-for-High: Efficient Boundary Detection from Deep Object Features and Its Applications to High-Level Vision (2015, methodology): “The most similar to our approach is DeepEdge [3], which uses a multi-scale bifurcated network to perform contour detection using object-level features.”
Efficient Decomposition of Image and Mesh Graphs by Lifted Multicuts (2015, methodology): “Our experiments are based on [20] which is publicly available and outperformed marginally by [15, 21].”
RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth (2021, background): “CNN-based edge detectors [3, 4, 9, 10, 17, 20, 24, 26, 31, 36, 45] do not rely on hand-crafted features and achieve better performance.”
Automatic autonomous vision-based power line inspection: A review of current status and the potential role of deep learning (2018, methodology): “First, outputs from edge detection algorithms, for instance the Canny edge detector [86], Matched filter [87], and Holistically-Nested Edge Detection [61], contour detectors such as, DeepEdge [62] and DeepContour [63], and/or line detectors, for example the Hough transform [64] and the Radon transfo”
Semantic Edge Detection with Diverse Deep Supervision (2018, methodology): “…et al. 2017; Yu et al. 2017) is an active computer vision research topic due to its wide-ranging applications, including object proposal generation (Bertasius et al. 2015b), occlusion and depth reasoning (Amer et al. 2015; Bian et al. 2021), 3D reconstruction (Shan et al. 2014), object detection…”
Object Contour and Edge Detection with RefineContourNet (2019, unknown): “ge segmentation, reached impressive results. In recent years, edge detectors, such as DeepNet [14] and N4-Fields [11] have begun to use operations from CNNs to reach a higherlevel detection. DeepEdge [3] and DeepContour [27] are CNN applications that use more high-level features to extract contours,”
Multi-scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation (2017, background): “Skip-layer networks, where the feature maps derived from different levels of a primary network are jointly considered in an output layer, have also become very popular [22, 3].”