Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Wenyu 7bd1ef4a47 | 1 year ago | |
---|---|---|
.. | ||
_base_ | 1 year ago | |
README.md | 1 year ago | |
cascade_rcnn_vit_base_hrfpn_cae_1x_coco.yml | 1 year ago | |
cascade_rcnn_vit_large_hrfpn_cae_1x_coco.yml | 1 year ago | |
faster_rcnn_vit_base_fpn_cae_1x_coco.yml | 1 year ago |
Object detection is a central downstream task used to
test if pre-trained network parameters confer benefits, such
as improved accuracy or training speed. The complexity
of object detection methods can make this benchmarking
non-trivial when new architectures, such as Vision Transformer (ViT) models, arrive.
Backbone | Pretrained | Model | Scheduler | Images/GPU | Box AP | Config | Download |
---|---|---|---|---|---|---|---|
ViT-base | CAE | Cascade RCNN | 1x | 1 | 52.7 | config | model |
ViT-large | CAE | Cascade RCNN | 1x | 1 | 55.7 | config | model |
Notes:
@article{chen2022context,
title={Context autoencoder for self-supervised representation learning},
author={Chen, Xiaokang and Ding, Mingyu and Wang, Xiaodi and Xin, Ying and Mo, Shentong and Wang, Yunhao and Han, Shumin and Luo, Ping and Zeng, Gang and Wang, Jingdong},
journal={arXiv preprint arXiv:2202.03026},
year={2022}
}
@article{DBLP:journals/corr/abs-2111-11429,
author = {Yanghao Li and
Saining Xie and
Xinlei Chen and
Piotr Doll{\'{a}}r and
Kaiming He and
Ross B. Girshick},
title = {Benchmarking Detection Transfer Learning with Vision Transformers},
journal = {CoRR},
volume = {abs/2111.11429},
year = {2021},
url = {https://arxiv.org/abs/2111.11429},
eprinttype = {arXiv},
eprint = {2111.11429},
timestamp = {Fri, 26 Nov 2021 13:48:43 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2111-11429.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{Cai_2019,
title={Cascade R-CNN: High Quality Object Detection and Instance Segmentation},
ISSN={1939-3539},
url={http://dx.doi.org/10.1109/tpami.2019.2956516},
DOI={10.1109/tpami.2019.2956516},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
publisher={Institute of Electrical and Electronics Engineers (IEEE)},
author={Cai, Zhaowei and Vasconcelos, Nuno},
year={2019},
pages={1–1}
}
PaddleDetection是一个基于PaddlePaddle的目标检测端到端开发套件,在提供丰富的模型组件和测试基准的同时,注重端到端的产业落地应用,通过打造产业级特色模型|工具、建设产业应用范例等手段,帮助开发者实现数据准备、模型选型、模型训练、模型部署的全流程打通,快速进行落地应用。
Python Markdown C++ Text Shell other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》