Continuing SSL pre-training for ten epochs with a criterion that maximizes one-dimensional marginal entropies and minimizes pairwise covariances improves downstream ImageNet classification, especially with few labels.
For SimSiam, the semi-supervised experiments were not conducted in the original paper, and therefore we skip this in our experiments
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
-
Improving Pre-trained Self-Supervised Embeddings Through Effective Entropy Maximization
Continuing SSL pre-training for ten epochs with a criterion that maximizes one-dimensional marginal entropies and minimizes pairwise covariances improves downstream ImageNet classification, especially with few labels.