一、研究背景
论文链接:https://proceedings.mlr.press/v139/xu21e/xu21e.pdf 代码地址:https://github.com/idstcv/Dash 技术应用:https://modelscope.cn/models/damo/cv_manual_face-liveness_flrgb/summary
这篇论文创新性地提出用动态阈值(dynamic threshold)的方式筛选无标签样本进行半监督学习(semi-supervised learning,SSL)的方法,我们改造了半监督学习的训练框架,在训练过程中对无标签样本的选择策略进行了改进,通过动态变化的阈值来选择更有效的无标签样本进行训练。Dash 是一个通用策略,可以轻松与现有的半监督学习方法集成。实验方面,我们在 CIFAR-10, CIFAR-100, STL-10 和 SVHN 等标准数据集上充分验证了其有效性。理论方面,论文从非凸优化的角度证明了 Dash 算法的收敛性质。
https://modelscope.cn/models/damo/cv_resnet50_face-detection_retinaface/summary https://modelscope.cn/models/damo/cv_resnet101_face-detection_cvpr22papermogface/summary https://modelscope.cn/models/damo/cv_manual_face-detection_tinymog/summary https://modelscope.cn/models/damo/cv_manual_face-detection_ulfd/summary https://modelscope.cn/models/damo/cv_manual_face-detection_mtcnn/summary https://modelscope.cn/models/damo/cv_resnet_face-recognition_facemask/summary https://modelscope.cn/models/damo/cv_ir50_face-recognition_arcface/summary https://modelscope.cn/models/damo/cv_manual_face-liveness_flir/summary https://modelscope.cn/models/damo/cv_manual_face-liveness_flrgb/summary https://modelscope.cn/models/damo/cv_manual_facial-landmark-confidence_flcm/summary https://modelscope.cn/models/damo/cv_vgg19_facial-expression-recognition_fer/summary https://modelscope.cn/models/damo/cv_resnet34_face-attribute-recognition_fairface/summary