lapvqa-rrg / README.md
dmusingu's picture
Upload README.md with huggingface_hub
97451c6 verified
|
Raw
History Blame
1.12 kB
metadata
tags:
  - chest-xray
  - radiology
  - report-generation
  - mimic-cxr
license: apache-2.0

LAPVQA — Radiology Report Generation (Frozen Off-the-shelf Encoders)

Part of the LAPVQA collection.

Description

Generative decoder heads for Radiology Report Generation (RRG) on MIMIC-CXR, trained on top of five frozen off-the-shelf vision encoders. Each file contains the decoder weights; the encoder is not bundled.

Results (MIMIC-CXR test set)

Encoder BLEU-4 ROUGE-L RadGraph-s
CLIP ViT-L/14 0.034 0.168 0.197
Florence-2 0.035 0.169 0.205
SigLIP 0.036 0.168 0.211
CoCa 0.030 0.160 0.193
OWLv2 0.034 0.169 0.197

SigLIP achieves the best RadGraph-s (0.211) among all frozen encoders, consistent with its larger patch-token count (729 tokens at 384 px) providing finer spatial detail.

Files

File Encoder backbone
clip-vit-l14.pt CLIP ViT-L/14
siglip.pt SigLIP
florence2.pt Florence-2
coca.pt CoCa
owlv2.pt OWLv2