A Broader Study of Cross-Domain Few-Shot Learning
Authors:
- James V. CodellaJCJames V. Codella
Preprint
Abstract
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. This leads to the cross-domain few-shot learning problem, where there is a large shift between base and novel class domains. While investigations of the cross-domain few-shot scenario exist, these works are limited to natural images that still contain a high degree of visual similarity. No work yet exists that examines few-shot learning across different imaging methods seen in real world scenarios, such as aerial and medical imaging. In this paper, we propose the Broader Study of Cross-Domain Few-Shot Learning (BSCD-FSL) benchmark, consisting of image data from a diverse assortment of image acquisition methods. This includes natural images, such as crop disease images, but additionally those that present with an increasing dissimilarity to natural images, such as satellite images, dermatology images, and radiology images. 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. The results demonstrate that state-of-art meta-learning methods are surprisingly outperformed by earlier meta-learning approaches, and all meta-learning methods underperform in relation to simple fine-tuning by 12.8% average accuracy. Performance gains previously observed with methods specialized for cross-domain few-shot learning vanish in this more challenging benchmark. Finally, accuracy of all methods tend to correlate with dataset similarity to natural images, verifying the value of the benchmark to better represent the diversity of data seen in practice and guiding future research.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Baby steps towards few-shot learning with multiple semanticsPattern Recognition Letters, 2022
- Semi-Supervised Domain Adaptation via Minimax Entropy2019
- EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover ClassificationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019
- Edge-Labeling Graph Neural Network for Few-Shot Learning2019
- Machine Learning and Health Care Disparities in DermatologyJAMA Dermatology, 2018
- The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesionsScientific Data, 2018
- Low-Shot Learning from Imaginary Data2018
- Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images2017
- Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-Tuning2017
- Deep Residual Learning for Image Recognition2016