Delving into inter-image invariance for unsupervised visual representations

• Main Authors: Xie, Jiahao, Zhan, Xiaohang, Liu, Ziwei, Ong, Yew-Soon, Loy, Chen Change
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2023
• Subjects: Engineering::Computer science and engineering; Unsupervised Learning; Self-supervised Learning
• Online Access: https://hdl.handle.net/10356/170424
• Institution: Nanyang Technological University

Contrastive learning has recently shown immense potential in unsupervised visual representation learning. Existing studies in this track mainly focus on intra-image invariance learning. The learning typically uses rich intra-image transformations to construct positive pairs and then maximizes agreem...