Pei Wang, Hao Yang, Stefano Soatto, U San, Bernt Schiele, Nuno Vasconcelos, Zhaowei Cai, Gurumurthy Swaminathan, Aws Labs
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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/amazonresearch/omni-detr.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.16089")
get_code_for_paper("2203.16089")
have("2203.16089")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2203.16089.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2203.16089)
Connect an agent — have() is free.