Bootstrap Your Object Detector via Mixed Training
2021
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. The code and models will be made publicly available
at \url{https://github.com/MendelXu/MixTraining}.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
41
References
0
Citations
NaN
KQI