SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1912.07200 · 2019

A Broader Study of Cross-Domain Few-Shot Learning

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
IBM/cdfsl-benchmark pwc_unofficial 6 of 7
FunctionStatusWhere it lives
ResNet10 Ran IBM/cdfsl-benchmark/backbone.py
code served (permissive licence) · get_code("592e3a34636ae458")
euclidean_dist Ran IBM/cdfsl-benchmark/methods/protonet.py
code served (permissive licence) · get_code("4dd319c45d372246")
get_assigned_file Ran IBM/cdfsl-benchmark/io_utils.py
code served (permissive licence) · get_code("400a8db2fb9b1633")
get_resume_file Ran IBM/cdfsl-benchmark/io_utils.py
code served (permissive licence) · get_code("4bd64c34ba45e089")
one_hot Ran IBM/cdfsl-benchmark/utils.py
code served (permissive licence) · get_code("f1324589fc273593")
sparsity Ran IBM/cdfsl-benchmark/utils.py
code served (permissive licence) · get_code("de09514deda6f881")
parse_args Not yet run IBM/cdfsl-benchmark/io_utils.py
code served (permissive licence) · get_code("15c45627ecb64c8d")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1912.07200")
get_code_for_paper("1912.07200")
have("1912.07200")

Connect an agent — have() is free.