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.

168,878 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “PEDCC-Loss”

Incremental Classifier Learning Based on PEDCC-Loss and Cosine Distancecs.LG

Paper tackles catastrophic forgetting in incremental learning with improved cosine distance and PEDCC-Loss.

problem Tackles catastrophic forgetting in incremental learning.

method Ensemble method based on cosine distance and PEDCC-Loss.

result Outperforms recent methods in preserving old knowledge while learning new classes.

incremental learning catastrophic forgetting cosine distance PEDCC-Loss knowledge distillation

2019-06-11abs ↗pdf ↗

Semi-supervised learning method based on predefined evenly-distributed class centroidscs.LG

A semi-supervised learning method using predefined class centroids for image classification.

problem Reducing the need for labeled data in deep learning.

method Use a small number of labeled samples and data augmentation on unlabeled samples. Constrain all samples to predefined evenly-distributed class centroids (PEDCC) using loss functions.

result Achieves state-of-the-art results with minimal labeled data.

semi-supervised learning predefined centroids image classification data augmentation loss functions

2020-01-13abs ↗pdf ↗