國立成功大學 統計與資料科學學系

Abstract

With the rapid growth of deep learning-based applications for computer vision and image processing, several effective and efficient models such as ResNet, DenseNet, ResNeXt, and EfficientNet have been proposed to achieve SOTA performance on various tasks in supervised learning way. However, rare studies focus on pairwise learning for computer vision applications. In this talk, I will introduce a particular semi-supervised learning strategy, called pairwise learning, to learn the common feature representation for different image processing and computer vision applications. I will show how the pairwise learning is beneficial to autonomous driving, fake multimedia information detection, few-shot learning, and re-identification tasks, as well as bring some possible and potential research topics on deep pairwise learning in the future.