iiinova — where your digital self keeps evolving

Simon Ging

@simon.ging.ai

Doctoral Researcher in Computer Vision and Natural Language Processing.

Simon Ging @simon.ging.ai · 08/05/2025

Using this dataset, we train a generic CLIP model in 2 days on 1 server. With a 10M subset of living organisms, we train domain expert CLIP models excelling at fine-grained animal, plant, and fungi classification. Models are out now on huggingface! The dataset is coming soon.

001

Simon Ging @simon.ging.ai · 08/05/2025

Excited to release our models and preprint: "Using Knowledge Graphs to harvest datasets for efficient CLIP model training" We propose a dataset collection method using knowledge graphs and web image search, and create EntityNet-33M: a dataset of 33M images paired with 46M texts.

arxiv.org

Using Knowledge Graphs to harvest datasets for efficient CLIP model training

Training high-quality CLIP models typically requires enormous datasets, which limits the development of domain-specific models -- especially in areas that even the largest CLIP models do not cover wel...

212