This demonstrates the process of adapting a large scale pretrained model, MetaCLIP 2, for fine tuning a specific downstream task: image classification.

Coral-Health is an image classification vision-language encoder model fine-tuned from google/siglip2-base-patch16-224 for a single-label classification task. It is designed to classify coral reef images into two health conditions using the SiglipForImageClassification architecture.

A Gradio-based demonstration for the AllenAI Molmo2-8B multimodal model, enabling image QA, multi-image pointing, video QA, and temporal tracking. Users upload images or videos, provide natural language prompts.

Flood-Image-Detection is a vision-language encoder model fine-tuned from google/siglip2-base-patch16-512 for binary image classification. It is trained to detect whether an image contains a flooded scene or non-flooded environment. The model uses the SiglipForImageClassification architecture.

shoe-type-detection is a vision-language encoder model fine-tuned from google/siglip2-base-patch16-512 for multi-class image classification. It is trained to detect different types of shoes such as Ballet Flats, Boat Shoes, Brogues, Clogs, and Sneakers. The model uses the SiglipForImageClassification architecture.

Multilabel-Portrait-SigLIP2 is a vision-language model fine-tuned from google/siglip2-base-patch16-224 using the SiglipForImageClassification architecture. It classifies portrait-style images into one of the following visual portrait categories:

Multilabel-GeoSceneNet is a vision-language encoder model fine-tuned from google/siglip2-base-patch16-224 for multi-label image classification. It is designed to recognize and label multiple geographic or environmental elements in a single image using the SiglipForImageClassification architecture.

Fashion-Product-Usage is a vision-language model fine-tuned from google/siglip2-base-patch16-224 using the SiglipForImageClassification architecture. It classifies fashion product images based on their intended usage context.

Implementation of PaliGemma

PussyCat-vs-Doggie-SigLIP2 is an image classification vision-language encoder model fine-tuned from google/siglip2-base-patch16-224 for a single-label classification task. It is designed to classify images as either a cat or a dog using the SiglipForImageClassification architecture.

Leverage SigLIP 2's capabilities using LitServe.

🌍 Fine-tune MetaCLIP-2 for multilingual image classification on various tasks, enhancing performance with innovative training and data curation methods.