Recurrent affine transform encoder for image representation

• Main Authors: Liu, Letao, Jiang, Xudong, Saerbeck, Martin, Dauwels, Justin
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2023
• Subjects: Engineering::Electrical and electronic engineering; Canonical Image Base; Self-Supervised Learning
• Online Access: https://hdl.handle.net/10356/164994
• Institution: Nanyang Technological University

This paper proposes a Recurrent Affine Transform Encoder (RATE) that can be used for image representation learning. We propose a learning architecture that enables a CNN encoder to learn the affine transform parameter of images. The proposed learning architecture decomposes an affine transform matri...