Robust fine-tuning of zero-shot models. (arXiv:2109.01903v3 [cs.CV] UPDATED)

Web: http://arxiv.org/abs/2109.01903

Large pre-trained models such as CLIP or ALIGN offer consistent accuracy
across a range of data distributions when performing zero-shot inference (i.e.,
without fine-tuning on a specific dataset). Although existing fine-tuning
methods substantially improve accuracy on a given target distribution, they
often reduce robustness to distribution shifts. We address this tension by
introducing a simple and effective method for improving robustness while
fine-tuning: ensembling the weights of the zero-shot and fine-tuned models
(WiSE-FT). Compared to standard fine-tuning, WiSE-FT provides large …

arxiv cv fine fine-tuning models