Text encoders bottleneck compositionality in contrastive vision-language models
Amita Kamath, Jack Hessel, Kai-Wei Chang · 2023
Performant vision-language (VL) models like CLIP represent captions using a single vector.How much information about language is lost in this bottleneck?We first curate CompPrompts, a set of increasingly compositional image captions that VL models should be able to capture (e.g., single object, to ob-ject+property, to multiple interacting objects).Then, we train text-only recovery probes that aim to reconstruct captions from single-vector text representations produced by several VL models.This approach does not require images, allowing us to test on a broader range of scenes compared to prior work.We find that: 1) CLIP's text encoder falls short on more compositional inputs, including object relationships, attribute-object association, counting, and negations; 2) some text encoders work significantly better than others; and 3) text-only recovery performance predicts multimodal matching performance on ControlledImCaps: a new evaluation benchmark we collect and release consisting of fine-grained compositional images and captions.Specifically, our results suggest textonly recoverability is a necessary (but not sufficient) condition for modeling compositional factors in contrastive VL models.We release our datasets and code.