Datasets › FETA Car-Manuals

FETA Car-Manuals (FETA Car-Manuals dataset, image-text retrieval for foundation models' expert data performance.)

Introduced by Amit Alfassy et al. in FETA: Towards Specializing Foundation Models for Expert Task Applications8 Sep 2022 archive 2025-07-28

FETA benchmark focuses on text-to-image and image-to-text retrieval in public car manuals and sales catalogue brochures. The FETA Car-Manuals dataset consists of a total of 349 PDF documents from 5 car manufacturers, namely Nissan, Toyota, Mazda, Renault, Chevrolet.

Benchmarks archive 2025-07-28

All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Image Retrieval FETA Car-Manuals FETA's CLIP-MIL (Many-Shot Image-to-text) R@1 29 FETA: Towards Specializing Foundation Models for Expert... alfassy/FETA 1 Compare
Image-to-Text Retrieval FETA Car-Manuals FETA's CLIP-MIL (Many-Shot Image-to-text) R@1 35.5 FETA: Towards Specializing Foundation Models for Expert... alfassy/FETA 1 Compare

Papers archive 2025-07-28

1 shown of 1 paper with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 1. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
FETA: Towards Specializing Foundation Models for Expert Task Applications 1 2 8 Sep 2022 not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • FETA Car-Manuals

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections