SigLIP replaces softmax-based contrastive loss with a simple pairwise sigmoid loss for vision-language pre-training, decoupling batch size from normalization and reaching strong zero-shot performance with limited compute.
WIT: wikipedia-based image text dataset for multimodal multilingual machine learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2representative citing papers
ReasonCLIP-58M applies continual pretraining with visually grounded reasoning captions on 58M examples to improve CLIP-style models on commonsense and compositional reasoning tasks.
citing papers explorer
-
Sigmoid Loss for Language Image Pre-Training
SigLIP replaces softmax-based contrastive loss with a simple pairwise sigmoid loss for vision-language pre-training, decoupling batch size from normalization and reaching strong zero-shot performance with limited compute.
-
ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP
ReasonCLIP-58M applies continual pretraining with visually grounded reasoning captions on 58M examples to improve CLIP-style models on commonsense and compositional reasoning tasks.