arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.08149cs.CVcs.AIcs.LG
收藏

自监督类认知Few-Shot分类

Self-Supervised Class-Cognizant Few-Shot Classification

Delft University of Technology(代尔夫特理工大学);Shell Global Solutions International B.V.(壳牌全球解决方案国际有限公司)

Ojas Kishore Shirekar, Hadi Jamali-Rad

摘要:

无监督学习被认为是人类智能的黑暗物质。为了朝着这个方向发展,本文重点研究了从大量未标记数据中进行无监督学习,然后对下游分类任务进行Few-Shot微调。为此,我们扩展了最近的一项研究,通过迭代聚类和重新排序来结合类级别的认知,并通过扩大对比优化损失来解释它,从而采用对比学习进行自我监督的预训练。据我们所知,我们在标准和跨领域场景中的实验表明,我们在标准mini-ImageNet基准测试的(5路,1和5次)设置以及跨域CDFSL基准测试的(5路,5和20次)设置。我们的代码和实验可以在我们的GitHub存储库中找到:https://github.com/ojss/c3lr。

英文摘要:

Unsupervised learning is argued to be the dark matter of human intelligence. To build in this direction, this paper focuses on unsupervised learning from an abundance of unlabeled data followed by few-shot fine-tuning on a downstream classification task. To this aim, we extend a recent study on adopting contrastive learning for self-supervised pre-training by incorporating class-level cognizance through iterative clustering and re-ranking and by expanding the contrastive optimization loss to account for it. To our knowledge, our experimentation both in standard and cross-domain scenarios demonstrate that we set a new state-of-the-art (SoTA) in (5-way, 1 and 5-shot) settings of standard mini-ImageNet benchmark as well as the (5-way, 5 and 20-shot) settings of cross-domain CDFSL benchmark. Our code and experimentation can be found in our GitHub repository: https://github.com/ojss/c3lr.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑