Combining Domain-Specific Meta-Learners in the Parameter Space for Cross-Domain Few-Shot Classification

no code implementations • 31 Oct 2020 • Shuman Peng, Weilian Song, Martin Ester

The goal of few-shot classification is to learn a model that can classify novel classes using only a few training examples.

Classification Cross-Domain Few-Shot +3

Adversarial Inductive Transfer Learning with input and output space adaptation

no code implementations • 25 Sep 2019 • Hossein Sharifi-Noghabi, Shuman Peng, Olga Zolotareva, Colin C. Collins, Martin Ester

To the best of our knowledge, AITL is the first adversarial inductive transfer learning method to address both input and output discrepancies.

Domain Adaptation Multi-Task Learning