On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “RandAugment”

Unsupervised Data Augmentation for Consistency Trainingcs.LG

Improved semi-supervised learning with advanced data augmentation.

problem Enhancing deep learning models with limited labeled data.

method Substitutes simple noising operations with advanced data augmentation methods like RandAugment and back-translation.

result Achieves substantial improvements across multiple tasks and datasets.

semi-supervised learning data augmentation consistency training RandAugment back-translation

2019-04-29abs ↗pdf ↗

Self-training with Noisy Student improves ImageNet classificationcs.LG

Improved ImageNet classification with semi-supervised learning.

problem Image classification with limited labeled data.

method Noisy Student Training: semi-supervised learning with noisy student models.

result 88.4% top-1 accuracy on ImageNet, 2.0% better than state-of-the-art.

ImageNet semi-supervised learning self-training distillation augmentation

2019-11-11abs ↗pdf ↗