mIoU: 6.6
Papers with Code · CC BY-SA 4.0
Image Segmentation
Image Segmentation is a computer vision task that involves dividing an image into multiple segments or regions, each of which corresponds to a different object or part of an object. The goal of image segmentation is to assign a unique label or category to each pixel in the image, so that pixels with similar attributes are grouped together.
논문
S-measure: 0.903mIoU: 0.799E-measure: 0.943MAE: 0.021
MAE: 0.043IoU: 0.828F-measure: 0.906
mIoUPartS: 63.8
MAE: 0.054IoU: 0.798F-measure: 0.877
S-measure: 0.887mIoU: 0.788E-measure: 0.938MAE: 0.025
S-measure: 0.864mIoU: 0.742E-measure: 0.906MAE: 0.032
MAE: 0.047IoU: 0.815F-measure: 0.892
MAE: 0.065IoU: 0.790F-measure: 0.857
S-measure: 0.862mIoU: 0.736E-measure: 0.898MAE: 0.032
GFLOPs: 0.275
mIoUPartS: 54.4
mIoUPartS: 58.6
Dice: 0.9843
mask AP: 35.4