A Marr-inspired boundary-and-surface pretraining stage before contrastive learning yields 2x faster convergence on ResNet18 plus better downstream representations and robustness.
Emer- gence of shape bias in convolutional neural networks through activation sparsity, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Perceptual Inductive Bias Is What You Need Before Contrastive Learning
A Marr-inspired boundary-and-surface pretraining stage before contrastive learning yields 2x faster convergence on ResNet18 plus better downstream representations and robustness.