半监督学习的方法主要包括:生成式方法、基于图的方法、低密度分割法、基于分歧的方法。详情可参阅周志华老师的综述文章《A brief introduction to weakly supervised learning》。 迁移学习(transfer learning):迁移学习是近年来被广泛研究,风头正劲的学习范式,感觉已经成为一个独立的研究领域。其内在思想是借鉴人类「举一...
在论文的Related Work部分,主要介绍了以下几个方面的相关工作: 弱监督学习(Weakly-supervised learning):讨论了与弱到强学习相关的一种学习方法,即在训练时使用不完全或不可靠的标签。介绍了一些常用的方法,如自举法、噪声鲁棒性损失和噪声建模等。 学生-教师训练(Student-teacher training):描述了一种训练框架,先训练...
博士期间做了一些基于网络数据的弱监督学习(webly supervised learning)方面的工作和零示例学习方面的工作，然后自然而然做了一个把弱监督学习和零示例学习结合的工作，把所有种类划分成没有交集的基础种类和新种类。基础种类有标注良好的训练图片，是强监督数据。新种类有带噪音的网络图片，是弱监督数据。所有种类都有...
Weakly-supervised learningAmortized inferenceBenchmarkWe address the problem of 3D shape completion from sparse and noisy point clouds, a fundamental problem in computer vision and robotics. Recent approaches are either data-driven or learning-based: Data-driven approaches rely on a shape model whose ...
Weakly supervised learning generally faces challenges in applicability to various scenarios with diverse weak supervision and in scalability due to the complexity of existing algorithms, thereby hindering the practical deployment. This paper introduces a general framework for learning from weak super...
Weakly supervised learning generally faces challenges in applicability to various scenarios with diverse weak supervision and in scalability due to the complexity of existing algorithms, thereby hindering the practical deployment. This paper introduces a general framework for learning from weak supervision (...
3. Yan Liu, Zhijie Zhang, Li Niu, Junjie Chen, Liqing Zhang, “Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity”, NeurIPS, 2021. 4. Li Niu, “Weak Novel Categories without Tears: A Survey on Weak-Shot Learning”, arXiv preprint arXiv:2110.02651, 2021. ...
博士期间做了一些基于网络数据的弱监督学习(webly supervised learning)方面的工作和零示例学习方面的工作,然后自然而然做了一个把弱监督学习和零示例学习结合的工作,把所有种类划分成没有交集的基础种类和新种类。基础种类有标注良好的训练图片,是强监督数据。新种类有带噪音的网络图片,是弱监督数据。所有种类都有词...
Active LearningSemi-supervisedMachine LearningWeak SupervisionClassificationSupervised Learning requires a huge amount of labeled data, making efficient labeling one of the most critical components for the success of Machine Learning (ML). One well-known method to gain......
Leveraging weak supervision from rich user interactions to train robust deep neural network models for real-world applications