Research

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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

1 result for “Food101-N”

NoiseRank: Unsupervised Label Noise Reduction with Dependence Modelscs.CV

NoiseRank reduces label noise without supervision, improving classification accuracy.

problem Label noise in datasets from noisy channels.

method NoiseRank uses Markov Random Fields to estimate and rank instances based on their noise probability.

result NoiseRank improves classification accuracy on noisy datasets.

label noise unsupervised learning Markov Random Fields classification accuracy Food101-N

2020-03-15abs ↗pdf ↗