CascadeRCNN<T>
Models & Types · AiDotNet.ComputerVision.Detection.ObjectDetection.RCNN
Cascade R-CNN - Multi-stage object detection with progressive refinement.
Inheritance: ModelBase<T, Tensor<T>, Tensor<T>> → VisionTaskModelBase<T> → ObjectDetectorBase<T> → CascadeRCNN<T>
Implements: IDetectionTrainingModel<T>
For Beginners
Cascade R-CNN improves upon Faster R-CNN by using multiple detection stages, each trained with progressively higher IoU thresholds. This allows the model to produce higher quality detections through progressive refinement.
How It Works
Key features:
- Multiple cascade stages (typically 3) for progressive refinement
- Each stage uses higher IoU threshold for training
- Bounding boxes are refined at each stage
- Achieves higher accuracy than Faster R-CNN at slight speed cost
Reference: Cai and Vasconcelos, “Cascade R-CNN: Delving into High Quality Object Detection”, CVPR 2018
Constructors
| Constructor | Summary |
|---|---|
CascadeRCNN(ObjectDetectionOptions<T> options, int numStages) |
Creates a new Cascade R-CNN detector. |
Properties
| Property | Summary |
|---|---|
string Name { get; } |
Methods
| Method | Summary |
|---|---|
BatchDetectionResult<T> DetectBatch(Tensor<T> images, double confidenceThreshold, double nmsThreshold) |
|
DetectionResult<T> Detect(Tensor<T> image, double confidenceThreshold, double nmsThreshold) |
|
Task LoadWeightsAsync(string pathOrUrl, CancellationToken cancellationToken) |
|
void SaveWeights(string path) |
|
void TrainDetections(Tensor<T> input, DetectionTrainingBatch<T> targets) |
Trains the proposal network and every cascade stage with their published objectives. |