Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy. (arXiv:2203.17205v2 [cs.CV] UPDATED)

Self-supervised learning (SSL) methods aim to learn view-invariant
representations by maximizing the similarity between the features extracted
from different crops of the same image regardless of cropping size and content.
In essence, this strategy ignores the fact that two crops may truly contain
different image information, e.g., background and small objects, and thus tends
to restrain the diversity of the learned representations. In this work, we
address this issue by introducing a new self-supervised learning strategy,
LoGo, that explicitly reasons …

arxiv cv global learning self-supervised learning strategy supervised learning