Browse SoTA > Computer Vision > Few-Shot Learning > Cross-Domain Few-Shot

Cross-Domain Few-Shot

3 papers with code · Computer Vision
Subtask of Few-Shot Learning

Leaderboards

Greatest papers with code

Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation

ICLR 2020 hytseng0509/CrossDomainFewShot

Few-shot classification aims to recognize novel categories with only few labeled images in each class.

CROSS-DOMAIN FEW-SHOT DOMAIN GENERALIZATION

A Broader Study of Cross-Domain Few-Shot Learning

16 Dec 2019IBM/cdfsl-benchmark

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.

CROSS-DOMAIN FEW-SHOT LEARNING FEW-SHOT IMAGE CLASSIFICATION TRANSFER LEARNING

Cross-Domain Few-Shot Learning with Meta Fine-Tuning

21 May 2020johncai117/Meta-Fine-Tuning

In our final results, we combine the novel method with the baseline method in a simple ensemble, and achieve an average accuracy of 73. 78% on the benchmark.

CROSS-DOMAIN FEW-SHOT LEARNING DATA AUGMENTATION DOMAIN ADAPTATION TRANSFER LEARNING