MegDet: A Large Mini-Batch Object Detector

CVPR 2018 Chao PengTete XiaoZeming LiYuning JiangXiangyu ZhangKai JiaGang YuJian Sun

The improvements in recent CNN-based object detection works, from R-CNN [11], Fast/Faster R-CNN [10, 31] to recent Mask R-CNN [14] and RetinaNet [24], mainly come from new network, new framework, or novel loss design. But mini-batch size, a key factor in the training, has not been well studied... (read more)

PDF Abstract

Evaluation results from the paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.