Timezone: »

Bootstrap Your Object Detector via Mixed Training
Mengde Xu · Zheng Zhang · Fangyun Wei · Yutong Lin · Yue Cao · Stephen Lin · Han Hu · Xiang Bai


We introduce MixTraining, a new training paradigm for object detection that can improve the performance of existing detectors for free. MixTraining enhances data augmentation by utilizing augmentations of different strengths while excluding the strong augmentations of certain training samples that may be detrimental to training. In addition, it addresses localization noise and missing labels in human annotations by incorporating pseudo boxes that can compensate for these errors. Both of these MixTraining capabilities are made possible through bootstrapping on the detector, which can be used to predict the difficulty of training on a strong augmentation, as well as to generate reliable pseudo boxes thanks to the robustness of neural networks to labeling error. MixTraining is found to bring consistent improvements across various detectors on the COCO dataset. In particular, the performance of Faster R-CNN~\cite{ren2015faster} with a ResNet-50~\cite{he2016deep} backbone is improved from 41.7 mAP to 44.0 mAP, and the accuracy of Cascade-RCNN~\cite{cai2018cascade} with a Swin-Small~\cite{liu2021swin} backbone is raised from 50.9 mAP to 52.8 mAP.

Author Information

Mengde Xu (Huazhong University of Science and Technology)
Zheng Zhang (MSRA)
Fangyun Wei (Microsoft Research Asia)
Yutong Lin (Xi'an Jiaotong University)
Yue Cao (Microsoft Research)
Stephen Lin (Microsoft Research)
Han Hu (Microsoft Research Asia)
Xiang Bai (Huazhong University of Science and Technology)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors