None
DE
Why Vision-Language Models Are Shortsighted
[]
WebWire | Recent Headlines
Vision-language models like CLIP are the backbone of modern AI tools, powering everything from zero-shot image classification to text-to-image generators like Stable Diffusion.
But these models have a blind spot: their training is heavily dominated by images paired with short, simple captions.
However, our research identifies a hidden shortcut these models take: both human- and AI-generated long captions often begin with a one-sentence summary.
However, as the figure below demonstrates, while models like Long-CLIP and TULIP see their performance severely degrade in these scenarios, our proposed DeBias-CLIP model stays consistently accurate.
In the generation example below, DeBias-CLIP captures details that appear late in the prompt more accurately than other models.