wyharveychen/CloserLookFewShot

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1159 stars · 268 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Reference PyTorch implementation of the ICLR 2019 paper 'A Closer Look at Few-shot Classification', providing a testbed for empirical evaluation of few-shot image classification methods. It includes training, feature extraction, and testing pipelines across datasets like mini-ImageNet, CUB, and Omniglot.

Use cases

• reproduce few-shot classification baselines
• benchmark meta-learning methods on mini-ImageNet
• evaluate few-shot learning on CUB and Omniglot
• compare baseline vs meta-learning approaches
• run cross-domain few-shot experiments
• extract and save backbone features for fast testing

When to choose

• you need a standard testbed for few-shot classification research
• you want to reproduce or compare against the paper's published results
• you need ready-made data pipelines for mini-ImageNet, CUB, or Omniglot

When to avoid

• you need modern PyTorch support (the code targets PyTorch < 0.4)
• you want a production-ready or maintained library
• you need few-shot learning for non-image modalities

Facets

library · maturity maintenance

machine-learning deep-learning benchmarking machine-learning deep-learning computer-vision python few-shot-learning meta-learning pytorch iclr-2019 image-classification research-code benchmark research linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="wyharveychen/CloserLookFewShot")