Liang Liu, Jiangning Zhang, Zhenye Gan, Chengjie Wang, Guanzhong Tian, Yabiao Wang, Boshen Zhang, Wuhao Zhang, Wenbing Zhu
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.
Scale variation across object instances remains a key challenge in object detection task. Despite the remarkable progress made by modern detection models, this challenge is particularly evident in the semi-supervised case. While existing semi-supervised object detection methods rely on strict conditions to filter high-quality pseudo labels from network predictions, we observe that objects with extreme scale tend to have low confidence, resulting in a lack of positive supervision for these objects. In this paper, we propose a novel framework that addresses the scale variation problem by introducing a mixed scale teacher to improve pseudo label generation and scale-invariant learning. Additionally, we propose mining pseudo labels using score promotion of predictions across scales, which benefits from better predictions from mixed scale features. Our extensive experiments on MS COCO and PASCAL VOC benchmarks under various semi-supervised settings demonstrate that our method achieves new state-of-the-art performance. The code and models are available at https: //github.com/lliuz/MixTeacher.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2303.09061")
get_code_for_paper("2303.09061")
have("2303.09061")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2303.09061.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2303.09061)
Connect an agent — have() is free.