Deep learning has been the answer to many machine learning problems during the past two decades. However, it comes with two significant constraints: dependency on extensive …
Large pre-trained models such as CLIP or ALIGN offer consistent accuracy across a range of data distributions when performing zero-shot inference (ie, without fine-tuning on a specific …
Neural network classifiers can largely rely on simple spurious features, such as backgrounds, to make predictions. However, even in these cases, we show that they still …
Abstract Machine-learning models for medical tasks can match or surpass the performance of clinical experts. However, in settings differing from those of the training dataset, the …
Recent advances in transformer-based architectures have shown promise in several machine learning tasks. In the audio domain, such architectures have been successfully …
Transfer learning–ie, further fine-tuning a pre-trained model on a downstream task–can confer significant advantages, including improved downstream performance, faster …
A common approach to transfer learning under distribution shift is to fine-tune the last few layers of a pre-trained model, preserving learned features while also adapting to the new …
S Azizi, B Mustafa, F Ryan, Z Beaver… - Proceedings of the …, 2021 - openaccess.thecvf.com
Self-supervised pretraining followed by supervised fine-tuning has seen success in image recognition, especially when labeled examples are scarce, but has received limited attention …
Open-vocabulary models like CLIP achieve high accuracy across many image classification tasks. However, there are still settings where their zero-shot performance is far from optimal …