Key points are not available for this paper at this time.
The development of object detection in the era of deep learning, from R-CNN 11, Fast/Faster R-CNN 10, 31 to recent Mask R-CNN 14 and RetinaNet 24, mainly come from novel network, new framework, or loss design. However, mini-batch size, a key factor for the training of deep neural networks, has not been well studied for object detection. In this paper, we propose a Large Mini-Batch Object Detector (MegDet) to enable the training with a large mini-batch size up to 256, so that we can effectively utilize at most 128 GPUs to significantly shorten the training time. Technically, we suggest a warmup learning rate policy and Cross-GPU Batch Normalization, which together allow us to successfully train a large mini-batch detector in much less time (e.g., from 33 hours to 4 hours), and achieve even better accuracy. The MegDet is the backbone of our submission (mmAP 52.5%) to COCO 2017 Challenge, where we won the 1st place of Detection task.
Building similarity graph...
Analyzing shared references across papers
Loading...
Chao Peng
Tete Xiao
Zeming Li
Tsinghua University
Peking University
Building similarity graph...
Analyzing shared references across papers
Loading...
Peng et al. (Fri,) studied this question.
www.synapsesocial.com/papers/6a0a9bae36657de66c737629 — DOI: https://doi.org/10.1109/cvpr.2018.00647