To cope with real-world dynamics, an intelligent system needs to incrementally acquire,
update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as …

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 …

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 …