datasets:
- timm/imagenet-22k-wds
library_name: transformers
license: cc-by-nc-4.0
I-JEPA Model (Huge, fine-tuned on IN22K)
I-JEPA is a method for self-supervised learning. At a high level, I-JEPA predicts the representations of part of an image from the representations of other parts of the same image:
- without relying on pre-specified invariances to hand-crafted data transformations, which tend to be biased for particular downstream tasks,
- and without having the model fill in pixel-level details, which tend to result in learning less semantically meaningful representations.
How does it work?
As opposed to generative methods that have a pixel decoder, I-JEPA has a predictor that makes predictions in latent space. The predictor in I-JEPA can be seen as a primitive (and restricted) world-model that is able to model spatial uncertainty in a static image from a partially observable context. This world model is semantic in the sense that it predicts high level information about unseen regions in the image, rather than pixel-level details.
We trained a stochastic decoder that maps the I-JEPA predicted representations back in pixel space as sketches. The model correctly captures positional uncertainty and produces high-level object parts with the correct pose (e.g., dog’s head, wolf’s front legs).
Intended uses & limitations
I-JEPA can be used for image classification or feature extraction. This checkpoint in specific is intended for Feature Extraction.
How to use
Here is how to use this model to classify an image of the COCO 2017 dataset into one of the 1,000 ImageNet classes:
import requests
from PIL import Image
from transformers import AutoProcessor, IJepaForImageClassification
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
model_id = "jmtzt/ijepa_vith14_22k"
processor = AutoProcessor.from_pretrained(model_id)
model = IJepaForImageClassification.from_pretrained(model_id)
inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits
# model predicts one of the 1000 ImageNet classes
predicted_class_idx = logits.argmax(-1).item()
print("Predicted class:", model.config.id2label[predicted_class_idx])
BibTeX entry and citation info
If you use I-JEPA or this code in your work, please cite:
@article{assran2023self,
title={Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture},
author={Assran, Mahmoud and Duval, Quentin and Misra, Ishan and Bojanowski, Piotr and Vincent, Pascal and Rabbat, Michael and LeCun, Yann and Ballas, Nicolas},
journal={arXiv preprint arXiv:2301.08243},
year={2023}
}