A Benchmark for Cross-Domain Few-Shot Learning

Home

Discover

Bookmarks

Keep Up With Top Trending Papers In CS / AI / ML ...

Source arXiv

Computer Vision

Machine Learning

A Benchmark for Cross-Domain Few-Shot Learning

A Broader Study of Cross-Domain Few-Shot Learning

Cross-domain few-shot learning is a challenging few-shot learning problem, where there is a large shift between base and novel class domains.

Recent progress on few-shot learning largely relies on annotated data for meta-learning : base classes sampled from the same domain as the novel classes.

However, in many applications, collecting data for meta-learning is infeasible or impossible.

Extensive experiments on the proposed benchmark are performed to evaluate state-of-art meta-learning approaches, transfer learning approaches, and newer methods for cross-domain few-shot learning.

Authors

Yunhui Guo, Noel C. Codella, Leonid Karlinsky, James V. Codella, John R. Smith, Kate Saenko, Tajana Rosing, Rogerio Feris

◐ Recommended Members

◐ Latest Activity