search

marqo-ai / marqo-ecommerce-embeddings

State-of-the-art embedding models fine-tuned for the ecommerce domain. +67% increase in evaluation metrics vs ViT-B-16-SigLIP.
https://huggingface.co/collections/Marqo/marqo-ecommerce-embeddings-66f611b9bb9d035a8d164fbb
26 stars 1 forks source link

Comparision with Marqo Siglip #7

Open aretius opened 5 days ago

aretius commented 5 days ago

Hello Thanks for sharing the e-commerce embedding model thats beating SOTA by a nice margin. I wanted to understand how are the e-commerce embeddings different from Marqo Siglip trained earlier from a metric standpoint. Did you ever do a comparison on same data for retrieval/search?

jn2clark commented 4 days ago

Hi @aretius , there are a few differences. The main differences were the data sets. FashionSigLIP was trained with a smaller but richer dataset. This also changed how the loss was done between the two models. We used 7 text fields and 1 image field so the loss was all combinations of img and text as well as the mean of the text vectors (i.e. fused).

aretius commented 3 days ago

Got it so the dataset and loss was different. Did you also evaluate both models on text/image based retrieval? If yes what difference did you notice?