Deeply supervised salient object detection with short connections

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. read more

PDF Abstract CVPR 2017 PDF CVPR 2017 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
RGB Salient Object Detection DUTS-TE DSS MAE 0.065 # 12
F-measure 0.813 # 11
RGB Salient Object Detection SBU DSS Balanced Error Rate 7.00 # 4

Results from Other Papers

Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
RGB Salient Object Detection ISTD DSS Balanced Error Rate 10.48 # 7
RGB Salient Object Detection UCF DSS Balanced Error Rate 10.56 # 5