We consider the problem of omni-supervised object detection, which can use unlabeled, fully labeled and weakly labeled annotations, such as image tags, counts, points, etc., for object detection. This is enabled by a unified architecture, Omni-DETR, based on the recent progress on student-teacher framework and end-to-end transformer based object detection. Under this unified architecture, different types of weak labels can be leveraged to generate accurate pseudo labels, by a bipartite matching based filtering mechanism, for the model to learn. In the experiments, Omni-DETR has achieved state-of-the-art results on multiple datasets and settings. And we have found that weak annotations can help to improve detection performance and a mixture of them can achieve a better trade-off between annotation cost and accuracy than the standard complete annotation. These findings could encourage larger object detection datasets with mixture annotations. The code is available at https://github.com/amazon-research/omni-detr.
@article{arxiv.2203.16089,
title = {Omni-DETR: Omni-Supervised Object Detection with Transformers},
author = {Pei Wang and Zhaowei Cai and Hao Yang and Gurumurthy Swaminathan and Nuno Vasconcelos and Bernt Schiele and Stefano Soatto},
journal= {arXiv preprint arXiv:2203.16089},
year = {2022}
}