Semantic, Instance, and Panoptic Segmentation
Compare semantic, instance and panoptic label maps, inspect individual pixels, and understand dense predictions, mask IoU, Dice and boundary errors.
4 min readConcept
Explore machine learning concepts related to Segmentation. Clear explanations and practical insights.
Compare semantic, instance and panoptic label maps, inspect individual pixels, and understand dense predictions, mask IoU, Dice and boundary errors.
Follow coarse feature maps into aligned pixel predictions: nearest and bilinear interpolation, transposed convolution, output shapes, skip fusion, and resizing logits before selecting labels.