Feature Corrective Transfer Learning: End-to-End Solutions to Object Detection in Non-Ideal Visual Conditions

arXiv:2404.11214v1 Announce Type: new
Abstract: A significant challenge in the field of object detection lies in the system's performance under non-ideal imaging conditions, such as rain, fog, low illumination, or raw Bayer images that lack ISP processing. Our study introduces "Feature Corrective Transfer Learning", a novel approach that leverages transfer learning and a bespoke loss function to facilitate the end-to-end detection of objects in these challenging scenarios without the need to convert non-ideal images into their RGB counterparts. In our …

abstract arxiv challenge cs.ai cs.cv detection feature images imaging lies low novel object performance processing rain raw solutions s performance study transfer transfer learning type visual