Skip to page content
SAVRN
Search Plan a project

Dataset · Image feature extraction

ORCA-3DCT

by Liang Renjie LiangRenjie/ORCA-3DCT

ORCA-3DCT — precomputed 3D CT visual tokens & Data Encoder outputs for the whole of CT-RATE, released so that work on 3D CT token compression, pooling, retrieval and probing does not have to start by spending several hundred GPU-hours re-encoding the corpus.

Rows—
Configurations—
Size10K<n<100K
Licensecc-by-nc-sa-4.0
AccessPublicly accessible
Monthly Downloads721

Dataset Card

ORCA-3DCT — precomputed 3D CT visual tokens & Data Encoder outputs for the whole of CT-RATE, released so that work on 3D CT token compression, pooling, retrieval and probing does not have to start by spending several hundred GPU-hours re-encoding the corpus. ctrate/uncompressed/ — the raw encoder grids, plus the pooled encoders' native output. Bring your own compressor. ctrate/compressed/ — ORCA and grid-average token

Excerpt from the card by Liang Renjie, licensed cc-by-nc-sa-4.0.

Details

Repository
LiangRenjie/ORCA-3DCT
Publisher
Liang Renjie
Task category
Image feature extraction
Tags
medical, 3d-ct, radiology
Size category
10K<n<100K
Languages
en
Revision
7dbe40110fd5309f1c9584e40bd5d22f7d0dbef6
Last updated
2026-09-30

License and Download

License
cc-by-nc-sa-4.0
Access
No access gate
Download from Liang Renjie

Released by Liang Renjie through its official repository on Hugging Face.