关于GCU、沐曦GPGPU、MLU、0卡V100资源4月7日恢复上架的公告>>> 关于共建具身智能开源数据集的倡议>>> 关于云脑任务中统一路径访问方式的公告>>> 关于将启智集群GPU资源迁移至智算集群的公告>>>
shyann_wong
  • Joined on Oct 16, 2022
  • Organization
Public Activity Repositories Datasets Starred Repositories
0
 Following
0
 Followers
0
 Achievement Badge
0
Recently updated
Sort
Newest Oldest Alphabetically Reverse alphabetically Recently updated Least recently updated Most stars Fewest stars Most forks Fewest forks
MSSHEM
1 0 0

该算法提出了一个新颖的、鲁棒的训练框架，可以提升模型在基于 OCR 识别文本的下游任务表现。该框架：1）采用简单而有效的方法，从干净的文本中直接模拟自然的 OCR 噪音，2）从大量的模拟样本中反复挖掘难样本，以获得最佳性能。3）采用稳定性损失，使模型学习到不受噪音表征的影响。在 Metaphor 数据集上 accuracy 达到 87.7%，F1 达到 87.1%。

Updated 1 year ago

Please read the following content carefully:

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》

Agree and continue
Disagree, exit