Gaussian-centered cropping variants are claimed to improve contrastive learning accuracy on small-image benchmarks over random cropping, with gains of 2.7 to 12.4 points on CIFAR-10.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Taming the Randomness: Towards Label-Preserving Cropping in Contrastive Learning
Gaussian-centered cropping variants are claimed to improve contrastive learning accuracy on small-image benchmarks over random cropping, with gains of 2.7 to 12.4 points on CIFAR-10.