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.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

1 result for “AugDrop”

WeMix: How to Better Utilize Data Augmentationcs.LG

WeMix improves data augmentation by correcting bias in deep learning.

problem Data augmentation's effectiveness is limited by data bias.

method Developed AugDrop and MixLoss algorithms to correct data bias.

result WeMix improves data augmentation performance through bias correction.

data augmentation bias correction deep learning data bias AugDrop

2020-10-03abs ↗pdf ↗