Self-supervised representation learning by predicting visual permutations

作者：

Highlights：

• The proposed method is capable of handling the whole space of permutations.

• The designed architecture is flexible and extensible.

• Our method achieved the state-of-the-art performance on STL-10.

• Our method is generic to solve ranking problem.

摘要

•The proposed method is capable of handling the whole space of permutations.•The designed architecture is flexible and extensible.•Our method achieved the state-of-the-art performance on STL-10.•Our method is generic to solve ranking problem.

论文关键词：Unsupervised representation learning,Self-supervised learning,Jigsaw puzzle reassembly,Multi-task learning,Permutation prediction

论文评审过程：Received 18 October 2019, Revised 26 September 2020, Accepted 13 October 2020, Available online 14 October 2020, Version of Record 16 October 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2020.106534