arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2108.00475cs.CVeess.IV
收藏

具有局部注意特征的自监督学习

Self-supervised Learning with Local Attention-Aware Feature

Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院)

Trung X. Pham, Rusty John Lloyd Mina, Dias Issa, Chang D. Yoo

摘要:

在这项工作中,我们提出了一种新的方法自监督学习产生全球和当地的注意力感知视觉功能。我们的方法是基于训练一个模型,以区分输入样本的特定图像变换和修补图像。利用这种方法,所提出的方法能够在Tiny-ImageNet数据集上超过之前最好的竞争对手1.03%,在STL-10数据集上超过2.32%。此外,我们的方法优于STL-10数据集上的全监督学习方法。实验结果和可视化显示的能力,成功地学习全球和当地的注意感知视觉表示。

英文摘要:

In this work, we propose a novel methodology for self-supervised learning for generating global and local attention-aware visual features. Our approach is based on training a model to differentiate between specific image transformations of an input sample and the patched images. Utilizing this approach, the proposed method is able to outperform the previous best competitor by 1.03% on the Tiny-ImageNet dataset and by 2.32% on the STL-10 dataset. Furthermore, our approach outperforms the fully-supervised learning method on the STL-10 dataset. Experimental results and visualizations show the capability of successfully learning global and local attention-aware visual representations.

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。

↑