Pixel Accuracy: 38.8
Papers with Code · CC BY-SA 4.0
Unsupervised Semantic Segmentation
Models that learn to segment each image (i.e. assign a class to every pixel) without seeing the ground truth labels.
<span style="color:grey; opacity: 0.6">( Image credit: SegSort: Segmentation by Discriminative Sorting of Segments )</span>
논문
mIoU: 16.7
Pixel Accuracy: 27.7
Accuracy: 83.3mIoU: 71.0
mIoU: 21.2Pixel Accuracy: 75.2
Pixel Accuracy: 69.98mIoU: 34.02
Pixel Accuracy: 65.48mIoU: 30.78
Pixel Accuracy: 31.0
Pixel Accuracy: 72.9
Accuracy: 83.3mIoU: 71.1
Accuracy: 82.0
mIoU (val): 11.5mIoU (test): 11.0
Accuracy: 82.4
Pixel Accuracy: 80.3
mIoU: 12.7Pixel Accuracy: 64.3
Pixel Accuracy: 74.6
mIoU: 3.7Pixel Accuracy: 8.8
Accuracy: 77.0