filipradenovic/cnnimageretrieval-pytorch

Health v2 · maintenance only

Adoption not part of the score

1495 stars · 318 forks observed · 2026-08-28

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

A PyTorch toolbox for training and evaluating convolutional neural networks for image retrieval, implementing the authors' TPAMI 2018 and ECCV 2016 papers. It supports fine-tuning CNNs, learning supervised whitening for global image descriptors, and benchmarking on Oxford and Paris datasets.

Use cases

• train a CNN for image retrieval in pytorch
• evaluate image retrieval on Oxford and Paris datasets
• fine-tune pretrained networks with no human annotation
• learn supervised whitening for global image descriptors
• extract global image descriptors for similarity search
• reproduce CNN image retrieval research papers

When to avoid

• you need modern transformer-based retrieval models like CLIP or DINO
• you want local feature matching rather than global descriptors
• you need a production-ready retrieval service rather than research code
• you work outside PyTorch

Facets

library · maturity maintenance

machine-learning deep-learning image-processing search-engine computer-vision image-processing deep-learning machine-learning python cross-platform image-retrieval pytorch cnn fine-tuning global-descriptors whitening oxford-paris-benchmark research-code gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="filipradenovic/cnnimageretrieval-pytorch")