Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples

This paper proposes a novel method of learning by predicting view assignments with support samples (PAWS). The method trains a model to minimize a consistency loss, which ensures that different views of the same unlabeled instance are assigned similar pseudo-labels... (read more)

PDF Abstract

Datasets


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Classification ImageNet PAWS (ResNet-50, 1% labels) Top 1 Accuracy 66.5% # 358
Image Classification ImageNet PAWS (ResNet-50, 10% labels) Top 1 Accuracy 75.5% # 311

Methods used in the Paper


METHOD TYPE
BYOL
Self-Supervised Learning
LARS
Large Batch Optimization
SwAV
Self-Supervised Learning