GLAMI-1M: A Multilingual Image-Text Fashion Dataset

11/17/2022

∙

by   Vaclav Kosar, et al.

∙

1

∙

share

We introduce GLAMI-1M: the largest multilingual image-text classification dataset and benchmark. The dataset contains images of fashion products with item descriptions, each in 1 of 13 languages. Categorization into 191 classes has high-quality annotations: all 100k images in the test set and 75 training set were human-labeled. The paper presents baselines for image-text classification showing that the dataset presents a challenging fine-grained classification problem: The best scoring EmbraceNet model using both visual and textual features achieves 69.7 model show the dataset is also suitable for image generation conditioned on text. The dataset, source code and model checkpoints are published at https://github.com/glami/glami-1m