2021/06/30 by Emanuele Sansone, Sansone, Emanuele
Computer Science · #Domain Adaptation and Few-Shot Learning #Multimodal Machine Learning Applications #Human Pose and Action Recognition
paper · pdf · doi:10.48550/arxiv.2106.16060
This work considers the problem of learning structured representations from raw images using self-supervised learning. We propose a principled framework based on a mutual information objective, which integrates self-supervised and structure learning. Furthermore, we devise a post-hoc procedure to interpret the meaning of the learnt representations. Preliminary experiments on CIFAR-10 show that the proposed framework achieves higher generalization performance in downstream classification tasks and provides more interpretable representations compared to the ones learnt through traditional self-supervised learning.