Is a Caption Worth a Thousand Images? A Controlled Study for Representation Learning
read the original abstract
The development of CLIP [Radford et al., 2021] has sparked a debate on whether language supervision can result in vision models with more transferable representations than traditional image-only methods. Our work studies this question through a carefully controlled comparison of two approaches in terms of their ability to learn representations that generalize to downstream classification tasks. We find that when the pre-training dataset meets certain criteria -- it is sufficiently large and contains descriptive captions with low variability -- image-only methods do not match CLIP's transfer performance, even when they are trained with more image data. However, contrary to what one might expect, there are practical settings in which these criteria are not met, wherein added supervision through captions is actually detrimental. Motivated by our findings, we devise simple prescriptions to enable CLIP to better leverage the language information present in existing pre-training datasets.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Demystifying CLIP Data
MetaCLIP curates balanced 400M-pair subsets from CommonCrawl that outperform CLIP data, reaching 70.8% zero-shot ImageNet accuracy on ViT-B versus CLIP's 68.3%.
-
OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models
OpenFlamingo provides open-source autoregressive vision-language models that achieve 80-89% of Flamingo performance on seven vision-language datasets.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.