Exploring DeshuffleGANs in Self-Supervised Generative Adversarial Networks
作者：
Highlights：
• We compare the deshuffling with the other self-supervision tasks on various datasets.
• We study the effects of deshuffling on training through 2 different networks unconditionally.
• We design the cDeshuffleGAN, the conditional version of the DeshuffleGANs.
• We evaluate the representation quality of the features learnt by the cDeshuffleGAN.
• We study the effects of self-supervision tasks on the loss landscape.
摘要
•We compare the deshuffling with the other self-supervision tasks on various datasets.•We study the effects of deshuffling on training through 2 different networks unconditionally.•We design the cDeshuffleGAN, the conditional version of the DeshuffleGANs.•We evaluate the representation quality of the features learnt by the cDeshuffleGAN.•We study the effects of self-supervision tasks on the loss landscape.
论文关键词：Self-Supervised generative adversarial networks,Generative adversarial networks,Self-supervised learning,DeshuffleGANs,Deshuffling
论文评审过程：Received 7 October 2020, Revised 3 May 2021, Accepted 6 August 2021, Available online 14 August 2021, Version of Record 22 August 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.108244
