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

2 results for “hardness-aware”

Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classificationcs.CV

Meta-learning strategy improves few-shot classification performance.

problem Few-shot classification with deep neural networks struggles when labeled samples are limited.

method Proposes an easy-to-hard expert meta-training strategy to arrange training tasks based on task hardness.

result Meta-learners achieve better results with the proposed expert training strategy.

meta-learning few-shot classification task hardness deep neural networks meta-training

2020-07-13abs ↗pdf ↗

Efficient Deep Representation Learning by Adaptive Latent Space Samplingcs.CV

Adaptive sampling improves deep learning efficiency by focusing on informative samples.

problem Expensive annotations and loss of sample informativeness in deep learning.

method Adaptive latent space sampling based on hardness-aware strategy.

result The proposed framework outperforms random sampling on various datasets.

deep learning annotation efficiency latent space hardness-aware sample selection

2020-03-19abs ↗pdf ↗