講 題：VIP: Visual Information Processing based on Pairwise Learning
主講人：許志仲 助理教授(國立成功大學數據科學研究所)
時 間：2022年04月21日（星期四）下午02：10 - 04：00
地 點：B302A（淡水校園商管大樓）
茶 會：2022年04月21日（星期四）下午01：30 (商管大樓 B1102)
摘 要
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 semi-supervised learning for computer vision applications.In this talk, I would like to 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 various computer vision tasks, as well as bring some possible and potential research topics on deep pairwise learning in the future.