Fetching the paper…

Reading the bibliography…

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

2020

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

Cai, John, Shen, Sheng Mei

Original
PDF
Post on X

Understand

In this paper, we tackle the new Cross-Domain Few-Shot Learning benchmark proposed by the CVPR 2020 Challenge.

To this end, we build upon state-of-the-art methods in domain adaptation and few-shot learning to create a system that can be trained to perform both tasks.
Inspired by the need to create models designed to be fine-tuned, we explore the integration of transfer-learning (fine-tuning) with meta-learning algorithms, to train a network that has specific layers that are designed to be adapted at a later fine-tuning stage.
To do so, we modify the episodic training process to include a first-order MAML-based meta-learning algorithm, and use a Graph Neural Network model as the subsequent meta-learning module.

Built on

Geometric deep learning: going beyond euclidean data
Michael M Bronstein, Joan Bruna, Yann LeCun, Arthur Szlam, and Pierre Vandergheynst · 2017
Earlier work this paper cites.
Model-agnostic meta-learning for fast adaptation of deep networks
Chelsea Finn, Pieter Abbeel, and Sergey Levine · 2017
Earlier work this paper cites.
Few-shot learning with graph neural networks
Original
Victor Garcia and Joan Bruna · 2017
Earlier work this paper cites.

Similar

On first-order meta-learning algorithms
Original
Alex Nichol, Joshua Achiam, and John Schulman · 2018
Cited alongside, same era.
A closer look at few-shot classification
Original
Wei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank Wang, and Jia-Bin Huang · 2019
Cited alongside, same era.
Diversity with cooperation: Ensemble methods for few-shot classification
Nikita Dvornik, Cordelia Schmid, and Julien Mairal · 2019
Cited alongside, same era.

Then

A new benchmark for evaluation of cross-domain few-shot learning
Original
Yunhui Guo, Noel CF Codella, Leonid Karlinsky, John R Smith, Tajana Rosing, and Rogerio Feris · 2019
Later among the works it cites.
Cross-domain few-shot classification via learned feature-wise transformation
Original
Hung-Yu Tseng, Hsin-Ying Lee, Jia-Bin Huang, and Ming-Hsuan Yang · 2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…