Real-time YOLO image segmentation
Go beyond bounding boxes with pixel-accurate masks. Ultralytics YOLO26 supports instance and semantic segmentation with the same fast training, validation, and deployment workflow as every YOLO task.
YOLO26 segmentation models
YOLO26-seg models detect objects and predict a pixel-accurate mask for each one, in five sizes from nano to extra-large. Box and mask accuracy are reported separately below; all sizes train, validate, and export through the standard Ultralytics workflow.
pip install ultralyticsfrom ultralytics import YOLO
# Load a YOLO26 segmentation model
model = YOLO("yolo26n-seg.pt")
# Run inference
results = model("image.jpg")| Model | Size (px) | mAP box (e2e) | mAP mask (e2e) | CPU ONNX (ms) | T4 TensorRT (ms) | Params (M) | FLOPs (B) |
|---|---|---|---|---|---|---|---|
| YOLO26n-seg | 640 | 39.6 | 33.9 | 53.3 ± 0.5 | 2.1 ± 0.0 | 2.7 | 9.1 |
| YOLO26s-seg | 640 | 47.3 | 40.0 | 118.4 ± 0.9 | 3.3 ± 0.0 | 10.4 | 34.2 |
| YOLO26m-seg | 640 | 52.5 | 44.1 | 328.2 ± 2.4 | 6.7 ± 0.1 | 23.6 | 121.5 |
| YOLO26l-seg | 640 | 54.4 | 45.5 | 387.0 ± 3.7 | 8.0 ± 0.1 | 28.0 | 139.8 |
| YOLO26x-seg | 640 | 56.5 | 47.0 | 787.0 ± 6.8 | 16.4 ± 0.1 | 62.8 | 313.5 |
YOLO26 instance segmentation benchmarks from the Ultralytics docs.
Trusted by the world's leading organizations
Our models' impact
Streamline processes across industries with our cutting-edge vision AI models. Speed, accuracy and ease-of-use powered by Ultralytics.
The evolution of Ultralytics YOLO models
See how Ultralytics YOLO evolved from the practical YOLOv5 workflow to edge-ready YOLO26 inference.
Label up to 10x faster with smart annotation
Ultralytics Platform gives you the image annotation tool to build high-quality datasets faster. From smart annotation to precise manual editing, these features are designed to reduce image labeling time without sacrificing quality.
- SAM-powered smart annotation: Masks and bounding boxes in one click.
- Full AI task coverage: Detection, instance segmentation, semantic segmentation, classification, pose, OBB.
- Universal format support: Your choice of YOLO, COCO, and more.
- Team review and versioning: Clear collaboration at every step.
Train on the Best GPUs for Less
26 NVIDIA GPUs starting at $0.24/hr — from Ampere to Blackwell. No markup, no minimums, no commitment.
Explore industry solutions
See how teams apply Ultralytics computer vision across production environments.
Agriculture
Automotive
Healthcare
Logistics
Manufacturing
Retail
Robotics
Agriculture
Automotive
Healthcare
Logistics
Manufacturing
Retail
Robotics
Agriculture
Automotive
Healthcare
Logistics
Manufacturing
Retail
Robotics
Frequently asked questions
Instance segmentation detects each object and outlines it with a pixel-accurate mask instead of only a bounding box. It is the right task when object shape, area, or boundaries matter — for example measuring items, separating touching objects, or masking regions for downstream processing. Ultralytics YOLO segmentation runs in real time with the same API as detection.
Instance segmentation produces a separate mask per object, so two adjacent cars get two masks. Semantic segmentation assigns a class label to every pixel in the scene without separating individual objects. Ultralytics YOLO26 supports both: use instance segmentation to count and track distinct objects, and semantic segmentation for full-scene understanding such as road or vegetation mapping.
Ultralytics YOLO26 segmentation models are the recommended starting point for new projects, from the nano size for edge devices to larger variants for accuracy-critical work. YOLO11 segmentation models remain supported through the same workflow.
Annotate masks and train with the Ultralytics library's train mode, or use Ultralytics Platform to annotate with smart polygon tools, train on cloud GPUs, and compare runs. Fine-tuning from pretrained segmentation weights converges quickly on most custom datasets.
Export trained models with export mode to ONNX, TensorRT, CoreML, OpenVINO, LiteRT, and more. Segmentation masks are produced natively by the exported model, so the deployment pipeline stays simple across edge, cloud, and mobile targets.
Build image segmentation with Ultralytics
Annotate masks, train YOLO26 segmentation models, and deploy them anywhere with Ultralytics Platform.