Yolov2 background affects object score

2 views (last 30 days)
gil
gil on 9 Dec 2021
Trained yolov2 detector using resnet50 network on artificial black rectangles (80 images over all 80 objects same rotation, size and content). The train set bounding boxes are a bit smaller than the black rectangle itself.(It happens also when the trained bounding box is a bit larger than the black rectangle.
[detector,~] = trainYOLOv2ObjectDetector(preprocessedTrainingData,lgraph,options);
Running detect and getting high score > 0.9 on specific object in an image see attached.
[bboxes,scores,labels] = detect(detector.detector, resized, "Threshold", 0);
On the same image artificially adding ellipses to the background near the object.
Run detect again and the score drops to < 0.3. see attached.
What can be the reason for the drop in the score? It looks like the close background like elipses impact the object score.
What MATLAB tools can be used to analyze this network?

Answers (0)

Tags

Products


Release

R2021b

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!