Texture and light are more important than color for defining the secret identity of a fashion house.
People usually identify brands like Tiffany or Hermès by their signature colors. New multimodal probing shows that AI actually identifies fashion brands primarily through the way light hits fabric textures. Color turns out to be a secondary feature that the model often ignores when making a final classification. This means the feel of the material is the most consistent marker of a brand's aesthetic DNA. Designers can use this insight to create more recognizable products that do not rely solely on a color palette. The machine has found a deeper signature of style than the human eye usually notices.
FASH-iCNN: Making Editorial Fashion Identity Inspectable Through Multimodal CNN Probing
arXiv · 2604.26186
Fashion AI systems routinely encode the aesthetic logic of specific houses, editors, and historical moments without disclosing it. We present FASH-iCNN, a multimodal system trained on 87,547 Vogue runway images across 15 fashion houses spanning 1991-2024 that makes this cultural logic inspectable. Given a photograph of a garment, the system recovers which house produced it, which era it belongs to, and which color tradition it reflects. A clothing-only model identifies the fashion house at 78.2%