Unsupervised representation learning by discovering reliable image relations

arXiv (Cornell University)(2020)

引用 8|浏览0
暂无评分
摘要
•Identify reliable image relations to drive unsupervised representation learning.•Divide-and-conquer strategy to retain only reliable relations between images.•Learning an ensemble of local representations by matching to random target embeddings.•Iterative extension of the set of reliable relations by inference.•Consolidate the local representations into one global representation by transitivity.
更多
查看译文
关键词
Unsupervised learning,Visual representation learning,Unsupervised image classification,Mining reliable relations,Divide-and-conquer
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要