YOLO11Seg<T>

Models & Types · AiDotNet.ComputerVision.Segmentation.InstanceSegmentation

YOLO11-Seg: Ultralytics next-generation real-time instance segmentation.

Inheritance: NeuralNetworkBase<T> → SegmentationModelBase<T> → InstanceSegmentationBase<T> → YOLO11Seg<T>

For Beginners

Real-time instance segmentation. Edge deployment with INT8 quantization.

Common use cases:

  • Real-time instance segmentation
  • Edge deployment with INT8 quantization
  • Video analytics pipelines
  • Mobile and embedded applications

How It Works

Technical Details:

  • C2PSA (Cross-Stage Partial with Spatial Attention) blocks
  • Improved feature pyramid for multi-scale detection
  • Anchor-free decoupled head with mask branch
  • YOLACT-style prototype mask generation

Reference: Ultralytics, “YOLO11”, 2024.

Example

// Create a YOLO11-Seg model for real-time instance segmentation
var architecture = new NeuralNetworkArchitecture<double>(
    inputType: InputType.ThreeDimensional,
    taskType: NeuralNetworkTaskType.MultiClassClassification,
    inputHeight: 640, inputWidth: 640, inputDepth: 3, outputSize: 80);
var model = new YOLO11Seg<double>(architecture);
// Every tunable is now set through the options object; these are the defaults:
var custom = new YOLO11Seg<double>(architecture,
    options: new YOLO11SegOptions { NumClasses = 80, DropRate = 0, ModelSize = YOLO11SegModelSize.N });
            
// Or load a pre-trained ONNX model for edge deployment
var onnxModel = new YOLO11Seg<double>(architecture, "yolo11n-seg.onnx");

Constructors

Constructor Summary
YOLO11Seg(NeuralNetworkArchitecture<T> architecture, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>> optimizer, ILossFunction<T> lossFunction, YOLO11SegOptions options) Initializes YOLO11Seg in native (trainable) mode.
YOLO11Seg(NeuralNetworkArchitecture<T> architecture, string onnxModelPath, YOLO11SegOptions options) Initializes YOLO11Seg in ONNX (inference-only) mode.

Methods

Method Summary
InstanceSegmentationResult<T> DetectInstances(Tensor<T> image)
ModelMetadata<T> GetModelMetadata() Collects metadata describing this model’s configuration.