About this document
VIPriors Object Detection Challenge Report by levi123 is a document available to read on EtoBox.
This document reports on a submission to the VIPriors Object Detection Challenge, focusing on the challenges of object detection with limited data and unbalanced categories. The authors propose effective data augmentation techniques and a suitable model for training from scratch, achieving improved average precision through careful network selection and enhancements like soft-NMS. The paper details various experiments and strategies that led to significant performance improvements in object detection tasks.
- Author
- levi123
- Language
- EN