DIoUNMS<T>

Models & Types · AiDotNet.ComputerVision.Detection.PostProcessing

Implements Distance-IoU based Non-Maximum Suppression for improved localization.

For Beginners

DIoU-NMS is an improved version of standard NMS that considers the distance between box centers, not just their overlap. This helps preserve nearby objects that might be suppressed by standard NMS.

How It Works

Reference: Zheng et al., “Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression”, AAAI 2020

Constructors

Constructor Summary
DIoUNMS() Creates a new DIoU-NMS instance.

Methods

Method Summary
List<Detection<T>> Apply(List<Detection<T>> detections, double diouThreshold) Applies DIoU-NMS to a list of detections.
List<Detection<T>> ApplyAdaptive(List<Detection<T>> detections, double baseDiouThreshold, double densityFactor) Applies DIoU-NMS with adaptive threshold based on box density.
List<Detection<T>> ApplyClassAware(List<Detection<T>> detections, double diouThreshold) Applies class-aware DIoU-NMS.
List<List<Detection<T>>> ApplyBatched(List<List<Detection<T>>> batchDetections, double diouThreshold, bool classAware) Applies batched DIoU-NMS for multiple images.