CoSal2015

ImagesIntroduced 2016-01-01

Cosal2015 is a large-scale dataset for co-saliency detection which consists of 2,015 images of 50 categories, and each group suffers from various challenging factors such as complex environments, occlusion issues, target appearance variations and background clutters, etc. All these increase the difficulty for accurate co-saliency detection.

Source: Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection Image Source: https://arxiv.org/pdf/1604.07090.pdf

Benchmarks

16k/max E-measure 16k/S-measure 16k/max F-measure 16k/MAE 16k/mean E-measure 16k/mean F-measure 2D Classification/max E-measure 2D Classification/S-measure 2D Classification/max F-measure 2D Classification/MAE 2D Classification/mean E-measure 2D Classification/mean F-measure 2D Object Detection/max E-measure 2D Object Detection/S-measure 2D Object Detection/max F-measure 2D Object Detection/MAE 2D Object Detection/mean E-measure 2D Object Detection/mean F-measure 3D/max E-measure 3D/S-measure 3D/max F-measure 3D/MAE 3D/mean E-measure 3D/mean F-measure Object Detection/max E-measure Object Detection/S-measure Object Detection/max F-measure Object Detection/MAE Object Detection/mean E-measure Object Detection/mean F-measure RGB Salient Object Detection/max E-measure RGB Salient Object Detection/S-measure RGB Salient Object Detection/max F-measure RGB Salient Object Detection/MAE RGB Salient Object Detection/mean E-measure RGB Salient Object Detection/mean F-measure Saliency Detection/max E-measure Saliency Detection/S-measure Saliency Detection/max F-measure Saliency Detection/MAE Saliency Detection/mean E-measure Saliency Detection/mean F-measure