arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.04789stat.MLcs.LG
收藏

利用图过滤提高分类精度

Improving Classification Accuracy with Graph Filtering

IMT Atlantique(大西洋矿业电信学院);Orange Labs(奥兰治实验室)

Mounia Hamidouche, Carlos Lassance, Yuqing Hu, Lucas Drumetz, Bastien Pasdeloup, Vincent Gripon

摘要:

在机器学习中,分类器通常对训练数据中的噪声敏感。在这项工作中,我们的目标是减少类内噪声的帮助下,图过滤,以提高分类性能。考虑图是通过连接属于同一类的训练集的样本,根据它们在潜在空间中的表示的相似性来获得的。我们表明,所提出的图过滤方法具有渐近减少类内方差的效果,同时保持均值。虽然我们的方法一般适用于所有分类问题,但它在Few-Shot设置中特别有用,其中类内噪声可能会由于小样本选择而产生巨大影响。使用标准化的基准领域的视觉,我们凭经验证明所提出的方法的能力,稍微提高国家的最先进的结果在这两种情况下的Few-Shot和标准分类。

英文摘要:

In machine learning, classifiers are typically susceptible to noise in the training data. In this work, we aim at reducing intra-class noise with the help of graph filtering to improve the classification performance. Considered graphs are obtained by connecting samples of the training set that belong to a same class depending on the similarity of their representation in a latent space. We show that the proposed graph filtering methodology has the effect of asymptotically reducing intra-class variance, while maintaining the mean. While our approach applies to all classification problems in general, it is particularly useful in few-shot settings, where intra-class noise can have a huge impact due to the small sample selection. Using standardized benchmarks in the field of vision, we empirically demonstrate the ability of the proposed method to slightly improve state-of-the-art results in both cases of few-shot and standard classification.

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。

↑