Uncertainty Estimation and Confidence Calibration in YOLO5Face
2024 (English)Independent thesis Advanced level (degree of Master (Two Years)), 28 HE credits
Student thesis
Abstract [en]
This thesis investigates predicting the Intersection over Union (IoU) in detections made by the face detector YOLO5Face, which is done to use the predicted IoU as a new uncertainty measure. The detections are done on the face dataset WIDER FACE, and the prediction of IoU is made by adding a parallel head to the existing YOLO5Face architecture. Experiments show that the methodology for predicting the IoU used in this thesis does not work and the parallel prediction head fails to predict the IoU and instead resorts to predicting common IoU values.
The localisation confidence and classification confidences of YOLO5Face are then investigated to find out which confidence measure is least uncertain and most suitable to use when identifying faces. Experiments show that the localisation confidence is consistently more calibrated than the classification confidence. The classification confidence is then calibrated with respect to the localisation confidence which reduces the Expected Calibration Error (ECE) for classification confidence from 0.17 to 0.01.
Place, publisher, year, edition, pages
2024. , p. 45
Keywords [en]
Computer Vision, Machine Learning, YOLO, YOLOv5, YOLO5Face, Uncertainty Estimation, Confidence Calibration, Face Detection, Temperature Scaling, Object Detection, Neural Networks, IoU, Predicting IoU, IoU prediction
National Category
Computer graphics and computer vision Computer Sciences Computer Systems Signal Processing
Identifiers
URN: urn:nbn:se:liu:diva-204951ISRN: LiTH-ISY-EX--24/5703--SEOAI: oai:DiVA.org:liu-204951DiVA, id: diva2:1871866
Subject / course
Computer Vision Laboratory
Presentation
2024-06-17, Visionen stora konferensrummet, LiU Campus Valla, Linköping, 13:00 (English)
Supervisors
Examiners
2024-06-182024-06-172025-02-01Bibliographically approved