RF-DETR Seg — Segmentation AI Model

RF-DETR Seg Medium returns a separate mask per instance across the 80 COCO categories, so two overlapping people come back as two objects rather than one blob. Real-time, with a DINOv2 backbone and a mask head.

Try in Studio

Details

  • CategorySegmentation
  • Year2026
  • LicenseApache-2.0

Compliance & Provenance

  • ProviderRoboflow (open) · Specialized
  • EU AI Act RiskMinimal Risk
  • Art. 50 TransparencyNot applicable

Inputs & Outputs

  • ImageInput · image

    Source image for instance segmentation

  • ImageOutput · image

    Per-instance masks rendered in distinct colors on a black background

  • TextOutput · string

    Detected instance labels with their mask color codes and confidence scores

Tags

  • instance-segmentation
  • segmentation
  • multi-object
  • mask
  • coco
  • real-time
  • transformer

Alternatives in Segmentation

  • BiRefNet (Subject)

    Cleanly extracts a single salient subject with high-resolution edges. ~1-3s.

  • SAM2 (Scene)

    Segment every object in an image (no labels needed). 10-30s.

  • SAM3 (Scene)

    Language-prompted segmentation (e.g. "person", "red car"). 10-30s/class.

  • SAM3.1 (Scene)

    Language-prompted segmentation — SAM 3.1 Object Multiplex with improved accuracy over SAM3. 10-30s/class.

Resources