DeepAI AI Chat
Log In Sign Up

Deeply supervised salient object detection with short connections

by   Qibin Hou, et al.
Nankai University

Recent progress on saliency detection is substantial, benefiting mostly from the explosive development of Convolutional Neural Networks (CNNs). Semantic segmentation and saliency detection algorithms developed lately have been mostly based on Fully Convolutional Neural Networks (FCNs). There is still a large room for improvement over the generic FCN models that do not explicitly deal with the scale-space problem. Holistically-Nested Edge Detector (HED) provides a skip-layer structure with deep supervision for edge and boundary detection, but the performance gain of HED on salience detection is not obvious. In this paper, we propose a new method for saliency detection by introducing short connections to the skip-layer structures within the HED architecture. Our framework provides rich multi-scale feature maps at each layer, a property that is critically needed to perform segment detection. Our method produces state-of-the-art results on 5 widely tested salient object detection benchmarks, with advantages in terms of efficiency (0.15 seconds per image), effectiveness, and simplicity over the existing algorithms.


page 2

page 6


Integrated Deep and Shallow Networks for Salient Object Detection

Deep convolutional neural network (CNN) based salient object detection m...

Investigating the feature collection for semantic segmentation via single skip connection

Since the study of deep convolutional neural network became prevalent, o...

Richer and Deeper Supervision Network for Salient Object Detection

Recent Salient Object Detection (SOD) systems are mostly based on Convol...

DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection

Recent progress on salient object detection mainly aims at exploiting ho...

Deep Crisp Boundaries: From Boundaries to Higher-level Tasks

Edge detection has made significant progress with the help of deep Convo...

Boundary-guided Feature Aggregation Network for Salient Object Detection

Fully convolutional networks (FCN) has significantly improved the perfor...

Deep Green Function Convolution for Improving Saliency in Convolutional Neural Networks

Current saliency methods require to learn large scale regional features ...