Downloads · 30 days
0
AmazonScience/MILE
MILE is a image feature extraction model from AmazonScience. Use it for the image feature extraction task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-nc-4.0.
Instructions for how to train and evaluate a MILE model, as well as the necessary code are in the Amazon Science repository.
Downloads · 30 days
0
Access
Public
Updated Nov 18, 2024
Repo size
6 GB
Likes
3
Public
Click a slice to open those files.
.pth6 GB · 100%
From the Hugging Face model README
Instructions for how to train and evaluate a MILE model, as well as the necessary code are in the Amazon Science repository.
These models have been trained on Amazon-Berkeley-Objects and iNaturalist and are intended to demonstrate the power of the object-level embeddings w.r.t. the object /category retrieval task. For other domains or tasks, it should be further fine-tuned on relevant data.
If you use this work, please cite:
@inproceedings{leotescu2024mile,
title={Self-Supervised Incremental Learning of Object Representations from Arbitrary Image Sets},
author={Leotescu, George and Popa, Alin-Ionut Popa and Grigore, Diana and Voinea, Daniel and Perona, Pietro},
booktitle={Proceedings of WACV},
year={2025}
}
This library is licensed under the CC BY NC License.