SAFT: Towards Out-of-Distribution Generalization in Fine-Tuning
This addresses the challenge of maintaining model robustness for real-world applications with distribution shifts, though it is incremental as it builds on existing fine-tuning and OOD generalization methods.
The paper tackles the problem of out-of-distribution generalization in fine-tuning pre-trained vision-language models like CLIP, where adaptation to downstream tasks degrades performance on OOD data, and introduces SAFT, a method that updates only 0.1% of parameters to improve OOD performance by 5.15% on average over conventional fine-tuning.
Handling distribution shifts from training data, known as out-of-distribution (OOD) generalization, poses a significant challenge in the field of machine learning. While a pre-trained vision-language model like CLIP has demonstrated remarkable zero-shot performance, further adaptation of the model to downstream tasks leads to undesirable degradation for OOD data. In this work, we introduce Sparse Adaptation for Fine-Tuning (SAFT), a method that prevents fine-tuning from forgetting the general knowledge in the pre-trained model. SAFT only updates a small subset of important parameters whose gradient magnitude is large, while keeping the other parameters frozen. SAFT is straightforward to implement and conceptually simple. Extensive experiments show that with only 0.1% of the model parameters, SAFT can significantly improve the performance of CLIP. It consistently outperforms baseline methods across several benchmarks. On the few-shot learning benchmark of ImageNet and its variants, SAFT gives a gain of 5.15% on average over the conventional fine-tuning method in OOD settings.