4 papers · 1 filter
MiSCHiEF: A Benchmark in Minimal-Pairs of Safety and Culture for Holistic Evaluation of Fine-Grained Image-Caption Alignment
Sagarika Banerjee, Tangatar Madi, Advait Swaminathan +4
Fine-grained image-caption alignment is crucial for vision-language models (VLMs), especially in socially critical contexts such as identifying real-world risk scenarios or disting…
Demystifying CLIP Data
Hu Xu, Saining Xie, Xiaoqing Ellen Tan +7
Contrastive Language-Image Pre-training (CLIP) is an approach that has advanced research and applications in computer vision, fueling modern recognition systems and generative mode…
Understanding Trade offs When Conditioning Synthetic Data
Brandon Trabucco, Qasim Wani, Benjamin Pikus +1
Learning robust object detectors from only a handful of images is a critical challenge in industrial vision systems, where collecting high quality training data can take months. Sy…
A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions
Jack Urbanek, Florian Bordes, Pietro Astolfi +3
Curation methods for massive vision-language datasets trade off between dataset size and quality. However, even the highest quality of available curated captions are far too short…