PictSure: In-context learning for image classification

Wolff, Cornelius; Schiesser, Lukas

PictSure is a deep learning library designed for in-context learning using images and labels. It allows users to provide a set of labeled reference images and then predict labels for new images based on those references. This approach eliminates the need for traditional training, making it highly adaptable for various classification tasks.

Additional Metadata
Rights	MIT License
Organisation	Database Architectures
Citation APA APA Style APA-ALL Style AAA Style Cell Style Chicago Style Harvard Style IEEE Style MLA Style Nature Style Vancouver Style American-Institute-of-Physics Style Council-of-Science-Editors Style BibTex Format Endnote Format RIS Format CSL Format DOIs only Format	Wolff, C.& Schiesser, L. (2025). PictSure: In-context learning for image classification.

Additional Files
View at Huggingface
View at GitHub

See Also
inProceedings PictSure: Pretraining embeddings matters for in-context learning image classifiers L. Schiesser (Lukas), C.U. Wolff (Cornelius), S. Haas (Sophie) and S. Pukrop (Simon)

PictSure: In-context learning for image classification

Publication

Publication

inProceedings
PictSure: Pretraining embeddings matters for in-context learning image classifiers

Address

CWI researchers

Questions or comments?

PictSure: In-context learning for image classification

Publication

Publication

inProceedings PictSure: Pretraining embeddings matters for in-context learning image classifiers

Workflow

Workflow

Add Content

inProceedings
PictSure: Pretraining embeddings matters for in-context learning image classifiers