Edit model card

Model Card: clip-imageclef

Model Details

OpenAI CLIP model fine-tuned using image-caption pairs from the Caption Prediction dataset provided for the ImageCLEF 2017 competition. The model was evaluated using before and after fine-tuning, MRR@10 were 0.57 and 0.88 respectively.

Model Date

September 6, 2021

Model Type

The base model is the OpenAI CLIP model. It uses a ViT-B/32 Transformer architecture as an image encoder and uses a masked self-attention Transformer as a text encoder. These encoders are trained to maximize the similarity of (image, text) pairs via a contrastive loss.


The fine-tuning can be reproduced using code from the Github repository elsevierlabs-os/clip-image-search.


from transformers import CLIPModel, CLIPProcessor

model = CLIPModel.from_pretrained("sujitpal/clip-imageclef")
processor = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
inputs = processor(text=captions, images=images, 
                   return_tensors="pt", padding=True)
output = model(**inputs)


Model-name k=1 k=3 k=5 k=10 k=20
zero-shot CLIP (baseline) 0.426 0.534 0.558 0.573 0.578
clip-imageclef (this model) 0.802 0.872 0.877 0.879 0.880
Downloads last month
Hosted inference API
This model can be loaded on the Inference API on-demand.