SSLPM, a self-supervised method that reduces redundancy by making features hard to predict from one another, matches state-of-the-art performance, but higher-order redundancy reduction does not clearly improve downstream accuracy.
Generative adversarial networks are special cases of artificial curiosity (1990) and also closely related to predictability minimization (1991).Neural Networks, 127:58–66,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Pairwise Correlations: Higher-Order Redundancies in Self-Supervised Representation Learning
SSLPM, a self-supervised method that reduces redundancy by making features hard to predict from one another, matches state-of-the-art performance, but higher-order redundancy reduction does not clearly improve downstream accuracy.