---
license: mit
datasets:
- imagenet-1k
language:
- en
metrics:
- accuracy
pipeline_tag: image-classification
tags:
- code
---
# Matryoshka Representation Learning🪆
_Aditya Kusupati*, Gantavya Bhatt*, Aniket Rege*, Matthew Wallingford, Aditya Sinha, Vivek Ramanujan, William Howard-Snyder, Kaifeng Chen, Sham Kakade, Prateek Jain, Ali Farhadi_

GitHub: https://github.com/RAIVNLab/MRL

Arxiv: https://arxiv.org/abs/2205.13147

We provide pretrained models trained with [FFCV](https://github.com/libffcv/ffcv) on ImageNet-1K:
1. `mrl` : ResNet50 __mrl__ models trained with Matryoshka loss (vanilla and efficient) with nesting starting from _d=8_ (default) and _d=16_
2. `fixed-feature` : independently trained ResNet50 baselines at _log(d)_ granularities
3. `resnet-family` : __mrl__ and __ff__ models trained on ResNet18/34/101

## Citation
If you find this project useful in your research, please consider citing:
```
@inproceedings{kusupati2022matryoshka,
  title     = {Matryoshka Representation Learning},
  author    = {Kusupati, Aditya and Bhatt, Gantavya and Rege, Aniket and Wallingford, Matthew and Sinha, Aditya and Ramanujan, Vivek and Howard-Snyder, William and Chen, Kaifeng and Kakade, Sham and Jain, Prateek and others},
  title     = {Matryoshka Representation Learning.},
  booktitle = {Advances in Neural Information Processing Systems},
  month     = {December},
  year      = {2022},
}
```