Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization
Keywords: Deep learning, computer vision, transfer learning, generalization, out-of-distribution, auxiliary trainings, ensembling, weight averaging, linear mode connectivity
TL;DR: We propose a new fine-tuning strategy that improves out-of-distribution generalization in computer vision by recycling and averaging weights specialized on diverse auxiliary tasks.
Abstract: Foundation models are redefining how AI systems are built. Practitioners now follow a standard procedure to build their machine learning solutions: from a pretrained foundation model, they fine-tune the weights on the target task of interest. So, the Internet is swarmed by a handful of foundation models fine-tuned on many diverse tasks: these individual fine-tunings exist in isolation without benefiting from each other. In our opinion, this is a missed opportunity, as these specialized models contain rich and diverse features. In this paper, we thus propose model ratatouille, a new strategy to recycle the multiple fine-tunings of the same foundation model on diverse auxiliary tasks. Specifically, we repurpose these auxiliary weights as initializations for multiple parallel fine-tunings on the target task; then, we average all fine-tuned weights to obtain the final model. This recycling strategy aims at maximizing the diversity in weights by leveraging the diversity in auxiliary tasks. Empirically, it improves the state of the art on the reference DomainBed benchmark for out-of-distribution generalization. Looking forward, this work contributes to the emerging paradigm of updatable machine learning where the community collaborates to reliably update machine learning models. Our code is released at https://github.com/facebookresearch/ModelRatatouille/.
Submission Number: 3
Loading