Self-supervised Learning with Local Attention-Aware Feature
It addresses visual representation learning for computer vision tasks, offering incremental gains over existing methods.
The paper tackles self-supervised learning for visual features by proposing a method to differentiate image transformations and patched images, achieving improvements of 1.03% on Tiny-ImageNet and 2.32% on STL-10, and outperforming fully-supervised learning on STL-10.
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.