Three Birds One Stone: A General Architecture for Salient Object Segmentation, Edge Detection and Skeleton Extraction

Abstract

In this paper, we aim at solving pixel-wise binary problems, including salient object segmentation, skeleton extraction, and edge detection, by introducing a unified architecture. Previous works have proposed tailored methods for solving each of the three tasks independently. Here, we show that these tasks share some similarities that can be exploited for developing a unified framework. In particular, we introduce a horizontal cascade, each component of which is densely connected to the outputs of previous component. Stringing these components together allows us to effectively exploit features across different levels hierarchically to effectively address the multiple pixel-wise binary regression tasks. To assess the performance of our proposed network on these tasks, we carry out exhaustive evaluations on multiple representative datasets. Although these tasks are inherently very different, we show that our unified approach performs very well on all of them and works far better than current single-purpose state-of-the-art methods. All the code in this paper will be publicly available.

References in corpus (11)

• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Richer Convolutional Features for Edge Detection
• Video Salient Object Detection via Fully Convolutional Networks
• Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation
• DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
• Visual Saliency Detection Based on Multiscale Deep CNN Features
• DISC: Deep Image Saliency Computing via Progressive Representation Learning
• DeepSkeleton: Learning Multi-task Scale-associated Deep Side Outputs for Object Skeleton Extraction in Natural Images
• Pixel-wise Deep Learning for Contour Detection
• Pushing the Boundaries of Boundary Detection using Deep Learning
• SRN: Side-output Residual Network for Object Symmetry Detection in the Wild

Cited by in corpus (6)

• Learning Part Boundaries from 3D Point Clouds
• Semantic Edge Detection with Diverse Deep Supervision
• Multi-Scale Iterative Refinement Network for RGB-D Salient Object Detection
• Highly Efficient Salient Object Detection with 100K Parameters
• A Simple Pooling-Based Design for Real-Time Salient Object Detection
• Deep Green Function Convolution for Improving Saliency in Convolutional Neural Networks