Video Polyp Segmentation On Sun Seg Hard
Métriques
Dice
S-Measure
Sensitivity
mean E-measure
mean F-measure
weighted F-measure
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
Nom du modèle | Dice | S-Measure | Sensitivity | mean E-measure | mean F-measure | weighted F-measure |
---|---|---|---|---|---|---|
Modèle 1 | 0.708 | 0.783 | 0.618 | 0.787 | 0.684 | 0.636 |
progressively-normalized-self-attention | 0.675 | 0.767 | 0.579 | 0.755 | 0.656 | 0.609 |
dynamic-context-sensitive-filtering-network | 0.317 | 0.514 | 0.364 | 0.522 | 0.303 | 0.263 |
the-emergence-of-objectness-learning-zero | 0.252 | 0.472 | 0.213 | 0.527 | 0.141 | 0.128 |
pranet-parallel-reverse-attention-network-for | 0.598 | 0.717 | 0.512 | 0.735 | 0.607 | 0.544 |
unet-a-nested-u-net-architecture-for-medical | - | - | 0.467 | - | - | - |
sali-short-term-alignment-and-long-term-1 | 0.822 | 0.874 | 0.830 | 0.920 | 0.822 | 0.790 |
matnet-motion-attentive-transition-network | 0.712 | 0.785 | 0.579 | 0.755 | 0.645 | 0.578 |
see-more-know-more-unsupervised-video-object-1 | 0.606 | 0.670 | 0.380 | 0.627 | 0.506 | 0.443 |
autosam-adapting-sam-to-medical-images-by | 0.759 | 0.822 | 0.726 | 0.866 | 0.764 | 0.714 |
Modèle 11 | 0.706 | 0.786 | 0.607 | 0.775 | 0.688 | 0.634 |
shallow-attention-network-for-polyp | 0.598 | 0.706 | 0.505 | 0.743 | 0.580 | 0.526 |
video-polyp-segmentation-a-deep-learning | 0.737 | 0.797 | 0.623 | 0.793 | 0.709 | 0.653 |
Modèle 14 | 0.584 | 0.682 | 0.415 | 0.660 | 0.510 | 0.443 |
lgrnet-local-global-reciprocal-network-for | 0.865 | - | - | - | - | - |
self-prompting-polyp-segmentation-in | 0.902 | 0.894 | 0.852 | 0.941 | 0.932 | - |
full-duplex-strategy-for-video-object | 0.699 | 0.724 | 0.491 | 0.694 | 0.611 | 0.541 |
u-net-convolutional-networks-for-biomedical | - | - | 0.429 | - | - | - |