issues
search
Understanding-Visual-Datasets
/
VisDiff
Official implementation of "Describing Differences in Image Sets with Natural Language" (CVPR 2024 Oral)
https://understanding-visual-datasets.github.io/VisDiff-website/
Apache License 2.0
105
stars
12
forks
source link
[WIP] Add GPT-4V support, correct data CSV's
#5
Closed
lisadunlap
closed
9 months ago
lisadunlap
commented
9 months ago
Added GPT-4V support for VLMProposer and captioner
corrected some incorrect file paths in ImageNetR
fixed difficulty level for PairedImageSets (need to check this is correct)
added license