Data-Efficient Instance Segmentation with a Single GPU
- URL: http://arxiv.org/abs/2110.00242v1
- Date: Fri, 1 Oct 2021 07:36:20 GMT
- Title: Data-Efficient Instance Segmentation with a Single GPU
- Authors: Pengyu Chen, Wanhua Li, Jiwen Lu
- Abstract summary: We introduce a data-efficient segmentation method we used in the 2021 VIPriors Instance Challenge.
Our solution is a modified version of Swin Transformer, based on the mmdetection which is a powerful toolbox.
Our method achieved the AP@0.50:0.95 (medium) of 0.592, which ranks second among all contestants.
- Score: 88.31338435907304
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Not everyone is wealthy enough to have hundreds of GPUs or TPUs. Therefore,
we've got to find a way out. In this paper, we introduce a data-efficient
instance segmentation method we used in the 2021 VIPriors Instance Segmentation
Challenge. Our solution is a modified version of Swin Transformer, based on the
mmdetection which is a powerful toolbox. To solve the problem of lack of data,
we utilize data augmentation including random flip and multiscale training to
train our model. During inference, multiscale fusion is used to boost the
performance. We only use a single GPU during the whole training and testing
stages. In the end, our team named THU_IVG_2018 achieved the result of 0.366
for AP@0.50:0.95 on the test set, which is competitive with other top-ranking
methods while only one GPU is used. Besides, our method achieved the
AP@0.50:0.95 (medium) of 0.592, which ranks second among all contestants
Related papers
Err
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.