Non-Local Deep Features for Salient Object Detection

Saliency detection aims to highlight the most relevant objects in an image. Methods using conventional models struggle whenever salient objects are pictured on top of a cluttered background while deep neural nets suffer from excess complexity and slow evaluation speeds. In this paper, we propose a simplified convolutional neural network which combines local and global information through a multi-resolution 4x5 grid structure. Instead of enforcing spacial coherence with a CRF or superpixels as is usually the case, we implemented a loss function inspired by the Mumford-Shah functional which penalizes errors on the boundary. We trained our model on the MSRA-B dataset, and tested it on six different saliency benchmark datasets. Results show that our method is on par with the state-of-the-art while reducing computation time by a factor of 18 to 100 times, enabling near real-time, high performance saliency detection.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Benchmark
RGB Salient Object Detection SOC NLDF S-Measure 0.816 # 5
mean E-Measure 0.837 # 5
Average MAE 0.106 # 5

Results from Other Papers

Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
RGB Salient Object Detection DUTS-TE NLDF MAE 0.065 # 24
max F-measure 0.816 # 16
RGB Salient Object Detection ISTD NLDF Balanced Error Rate 7.50 # 4
RGB Salient Object Detection SBU NLDF Balanced Error Rate 7.02 # 5
RGB Salient Object Detection UCF NLDF Balanced Error Rate 7.69 # 2


No methods listed for this paper. Add relevant methods here