Pixel-wise Deep Learning for Contour Detection

Abstract

We address the problem of contour detection via per-pixel classifications of edge point. To facilitate the process, the proposed approach leverages with DenseNet, an efficient implementation of multiscale convolutional neural networks (CNNs), to extract an informative feature vector for each pixel and uses an SVM classifier to accomplish contour detection. In the experiment of contour detection, we look into the effectiveness of combining per-pixel features from different CNN layers and verify their performance on BSDS500.

2 pages. arXiv admin note: substantial text overlap with arXiv:1412.6857

References in corpus (1)

• DenseNet: Implementing Efficient ConvNet Descriptor Pyramids

Cited by in corpus (19)

• Richer Convolutional Features for Edge Detection
• Holistically-Nested Edge Detection
• Dynamic Feature Integration for Simultaneous Detection of Salient Object, Edge and Skeleton
• PixelNet: Representation of the pixels, by the pixels, and for the pixels
• PixelNet: Towards a General Pixel-level Architecture
• Pushing the Boundaries of Boundary Detection using Deep Learning
• Flood-Filling Networks
• Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform
• CASENet: Deep Category-Aware Semantic Edge Detection
• InstanceCut: from Edges to Instances with MultiCut
• SREdgeNet: Edge Enhanced Single Image Super Resolution using Dense Edge Detection Network and Feature Merge Network
• Recent Advances in the Applications of Convolutional Neural Networks to Medical Image Contour Detection
• Three Birds One Stone: A General Architecture for Salient Object Segmentation, Edge Detection and Skeleton Extraction
• SegSort: Segmentation by Discriminative Sorting of Segments
• CAFENet: Class-Agnostic Few-Shot Edge Detection Network
• RED-NET: A Recursive Encoder-Decoder Network for Edge Detection
• DOOBNet: Deep Object Occlusion Boundary Detection from an Image
• Adversarial Structure Matching for Structured Prediction Tasks
• Boundary Distribution Estimation for Precise Object Detection