- 博客(7)
- 收藏
- 关注
原创 Multi-Objective Interpolation Training for Robustness to Label Noise
Multi-Objective Interpolation Training for Robustness to Label NoiseAbstractionIntroductionMethodAbstraction监督对比学习 + 插值训练IntroductionMulti-Objective Interpolation Training (MOIT), a framework to robustly learn in the prese of label noise by jointly ex
2021-12-02 20:12:32 1779 1
原创 论文阅读:Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterion
Towards Understanding Deep Learning from Noisy Labels with Small-Loss CriterionAbstractIntroductionMethodAbstractIn the past few years, deep learning methods for dealing with noisy labels have been developed, many of which are based on the small-loss cr
2021-12-01 17:17:36 953 1
原创 论文阅读:What Do Neural Networks Learn When Trained With Random Labels?
What Do Neural Networks LearnWhen Trained With Random Labels?AbstractWhen Trained With Random Labels?)内容整理自What Do Neural Networks LearnWhen Trained With Random Labels?.Abstractan alignment between the principal components of network parameters and
2021-11-29 15:39:42 325
原创 论文阅读:Learning from Noisy Labels with Complementary Loss Functions
@TOC整理了文章的关键内容,内容源自Jo-SRC: A Contrastive Approach for Combating Noisy Labels。Abstractwe train the net
2021-11-25 16:30:01 1047 1
原创 论文阅读Jo-SRC: A Contrastive Approach for Combating Noisy Labels
Jo-SRC: A Contrastive Approach for Combating Noisy LabelsAbstractMethod整理了文章的关键内容,内容源自Jo-SRC: A Contrastive Approach for Combating Noisy Labels。Abstractwe train the network in a contrastive learning manner对比学习Predictions from two different views of e
2021-11-20 11:11:34 2709
原创 论文阅读ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks
ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural NetworksAbstractIntroductionMathematical Analysis and TheoryProSelfLC: Progressive and Adaptive Label CorrectionExperiments小结整理了文章的关键内容,内容源自ProSelfLC: Progressive Self Label Corr
2021-11-17 20:14:38 1604
原创 论文阅读 DualGraph: A graph-based method for reasoning about label noise
DualGraph: A graph-based method for reasoning about label noise欢迎使用Markdown编辑器新的改变功能快捷键合理的创建标题,有助于目录的生成如何改变文本的样式插入链接与图片如何插入一段漂亮的代码片生成一个适合你的列表创建一个表格设定内容居中、居左、居右SmartyPants创建一个自定义列表如何创建一个注脚注释也是必不可少的KaTeX数学公式新的甘特图功能,丰富你的文章UML 图表FLowchart流程图导出与导入导出导入欢迎使用Markd
2021-11-11 15:25:48 630
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人