Canonical Color as a Lens into Concept Decodability in Vision Encoders and VLMs
Visual encoders construct a representation of the image input for Vision-Language models. How much conceptual, as opposed to immediately visible, information does this representation contain? We use canonical color as a controlled test case to ask whether vision encoders make canonical-color information linearly accessible, even when color is removed from the input image. We construct a dataset…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
