Saltar al contenido
Atlas de IA

Segmentación de imágenes

Etiquetar cada píxel con su objeto

Comprensión visualPrincipiante #13
entradaImagenImagen

El texto completo se presenta en inglés; el título y el resumen están traducidos.

QUÉ SIGNIFICA ESTA CAPACIDAD

Takes an image and outputs a mask the size of the input, labelling each pixel with its class or its instance. It is finer than detection because it gives outlines rather than boxes. Semantic segmentation only distinguishes classes (all of them are people), while instance segmentation also separates individuals (A and B are different people); the two are often lumped together as segmentation.

Cómo se consigue técnicamente

The classic design is an encoder–decoder: the encoder downsamples to extract semantics, the decoder upsamples to restore resolution, and skip connections carry high-resolution detail from shallow layers, with U-Net and fully convolutional networks as landmarks. Instance segmentation often detects first and predicts a mask inside each box (the Mask R-CNN line), or uses a promptable segment-anything model cued by clicks or boxes to isolate arbitrary objects.

Productos representativos

4

Organizaciones relacionadas

Usos típicos

  • Organ and lesion delineation in medical imaging
  • Land-cover classification in remote sensing
  • Drivable area and obstacles for driving
  • Selection masks for image editing

Cómo se evalúa

IoU / mIoU
Intersection over union of masks, averaged over classes
Dice coefficient
Common in medical imaging, more sensitive than IoU for small targets
Boundary F-score
Judges only contour fit rather than large correct interiors

Límites y dificultades

  • Thin structures and boundaries — hair, wires, vessel tips — break or lose their thinness
  • Adjacent or overlapping instances of the same class merge into one blob
  • Masks are inaccurate on transparent, reflective or low-contrast materials

Conceptos detrás