1st Place Solutions for UG2+ Challenge 2021 -- (Semi-)supervised Face detection in the low light condition
This work addresses face detection in low-light conditions for computer vision applications, representing an incremental improvement using existing methods on new data.
The team tackled face detection in low-light conditions by using image enhancement and transfer methods to align low-light and normal image domains, then trained object detection frameworks on this data. Their ensemble of models achieved 74.89 mAP on the testing set, securing first place in the UG2+ Challenge.
In this technical report, we briefly introduce the solution of our team "TAL-ai" for (Semi-) supervised Face detection in the low light condition in UG2+ Challenge in CVPR 2021. By conducting several experiments with popular image enhancement methods and image transfer methods, we pulled the low light image and the normal image to a more closer domain. And it is observed that using these data to training can achieve better performance. We also adapt several popular object detection frameworks, e.g., DetectoRS, Cascade-RCNN, and large backbone like Swin-transformer. Finally, we ensemble several models which achieved mAP 74.89 on the testing set, ranking 1st on the final leaderboard.