In healthcare, the development and deployment of insufficiently fair systems of artificial
intelligence (AI) can undermine the delivery of equitable care. Assessments of AI models …

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 …

While algorithmic fairness is a thriving area of research, in practice, mitigating issues of bias
often gets reduced to enforcing an arbitrarily chosen fairness metric, either by enforcing …

Empirical risk minimization (ERM) of neural networks is prone to over-reliance on spurious
correlations and poor generalization on minority groups. The recent deep feature …

In consequential decision-making applications, mitigating unwanted biases in machine
learning models that yield systematic disadvantage to members of groups delineated by …

Fine-tuning pre-trained vision-language models, like CLIP, has yielded success on diverse
downstream tasks. However, several pain points persist for this paradigm:(i) directly tuning …

Recent works have demonstrated that neural networks exhibit extreme* simplicity bias*(SB).
That is, they learn* only the simplest* features to solve a task at hand, even in the presence …

The task of infomin learning aims to learn a representation with high utility while being
uninformative about a specified target, with the latter achieved by minimising the mutual …

Transfer learning with a small amount of target data is an effective and common approach to
adapting a pre-trained model to distribution shifts. In some situations, target data labels may …

Open world object detection aims to identify objects of unseen categories and incrementally
recognize them once their annotations are provided. In distinction to the traditional paradigm …