Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference

Timothy Hospedales, Shell Hu, Da Li, Minyoung Kim, Jan Stühmer

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 19 functions out of this paper's own repositories and ran 14 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.

Repositories linked to this paper

• hushell/pmf_cvpr22 — marked official in Papers with Code; named in the paper

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

Abstract

Few-shot learning (FSL) is an important and topical problem in computer vision that has motivated extensive research into numerous methods spanning from sophisticated metalearning methods to simple transfer learning baselines. We seek to push the limits of a simple-but-effective pipeline for real-world few-shot image classification in practice. To this end, we explore few-shot learning from the perspective of neural architecture, as well as a three stage pipeline of pre-training on external data, meta-training with labelled few-shot tasks, and task-specific fine-tuning on unseen tasks. We investigate questions such as: 1 How pre-training on external data benefits FSL? 2 How state of the art transformer architectures can be exploited? and 3 How to best exploit fine-tuning? Ultimately, we show that a simple transformer-based pipeline yields surprisingly good performance on standard benchmarks such as Mini-ImageNet, CIFAR-FS, CDFSL and Meta-Dataset. Our code is available at https://hushell.github.io/pmf.

For agents

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

get_harvested_code_for_paper("2204.07305")
get_code_for_paper("2204.07305")
have("2204.07305")

Connect an agent — have() is free.