Computer Vision Experimentation Frameworks - Generalized-YOLOv5

Generalized-YOLOv5 is a modified version of YOLOv5. YOLOv5 itself is a realtime object detection framework designed for natural images. Our Generalized-YOLOv5 version has two crucial extensions. First, an extension that generalizes YOLOv5 also to non-natural images, which enables the usage of state-of-the-art realtime object detection to many domains (e.g. the medical domain). Second, an integration of N-fold cross-validation ensembles into the framework, improving the performance especially in low data regimes. Both contributions have been thoroughly tested in a series of experiments on a X-ray nodule dataset. All experiments alongside the insights discovered based on the experiments are included in the documentation.

Computer Vision Experimentation Frameworks - Generalized-YOLOv5 © Karol Gotkowski

Find Computer Vision Experimentation Frameworks - Generalized-YOLOv5 on Helmholtz Imaging Connect
Authors: Karol Gotkowski