See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks

Benchmark Model Rank Results
unsupervised-video-object-segmentation-on-10COSNet#15G: 80.0J: 80.5F: 79.4
unsupervised-video-object-segmentation-on-11COSNet#10J: 75.6
unsupervised-video-object-segmentation-on-12COSNet#10J: 70.5
video-polyp-segmentation-on-sun-seg-easyCOSNet#10Dice: 0.596S measure: 0.654mean E-measure: 0.600
video-polyp-segmentation-on-sun-seg-hardCOSNet#8Dice: 0.606S-Measure: 0.670mean E-measure: 0.627