# Do the Frankenstein, or how to achieve better out-of-distribution performance with manifold mixing model soup

arXiv: https://arxiv.org/abs/2309.08610 · HTML: https://mlsanity.com/paper/2309.08610/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 17 references that are in the map.
- First posted on arXiv 28 Aug 2023.

## Builds on (most cited first, 14 of 14)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)
- [Neural networks with late-phase weights](https://mlsanity.com/paper/2007.12927/) (2020)
- [PopulAtion Parameter Averaging (PAPA)](https://mlsanity.com/paper/2304.03094/) (2023)
- [Versatile Black-Box Optimization](https://mlsanity.com/paper/2004.14014/) (2020)

## Built on by (most cited first, 1 of 1)

- [Enhanced Soups for Graph Neural Networks](https://mlsanity.com/paper/2503.11612/) (2025)

## Abstract (arXiv)

The standard recipe applied in transfer learning is to finetune a pretrained model on the task-specific dataset with different hyperparameter settings and pick the model with the highest accuracy on the validation dataset. Unfortunately, this leads to models which do not perform well under distribution shifts, e.g. when the model is given graphical sketches of the object as input instead of photos. In order to address this, we propose the manifold mixing model soup, an algorithm which mixes together the latent space manifolds of multiple finetuned models in an optimal way in order to generate a fused model. We show that the fused model gives significantly better out-of-distribution performance (+3.5 % compared to best individual model) when finetuning a CLIP model for image classification. In addition, it provides also better accuracy on the original dataset where the finetuning has been done.