Generative modeling and representation learning are two key tasks in computer vision.
However, these models are typically trained independently, which ignores the potential for …

Real-world data often exhibits long tail distributions with heavy class imbalance, where the
majority classes can dominate the training process and alter the decision boundaries of the …

Autism spectrum disorder (ASD) is highly heterogeneous. Identifying systematic individual
differences in neuroanatomy could inform diagnosis and personalized interventions. The …

The generalization of representations learned via contrastive learning depends crucially on
what features of the data are extracted. However, we observe that the contrastive loss does …

Deep domain adaptation has achieved promising results in cross-domain hyperspectral
image (HSI) classification. However, existing methods often focus on aligning data …

Contrastive learning (CL) has emerged as a powerful technique for representation learning,
with or without label supervision. However, supervised CL is prone to collapsing …

Learning representations of images that are invariant to sensitive or unwanted attributes is
important for many tasks including bias removal and cross domain retrieval. Here, our …

The placenta is a valuable organ that can aid in understanding adverse events during
pregnancy and predicting issues post-birth. Manual pathological examination and report …

Whilst contrastive learning yields powerful representations by matching different augmented
views of the same instance, it lacks the ability to capture the similarities between different …

The standard placental examination helps identify adverse pregnancy outcomes but is not
scalable since it requires hospital-level equipment and expert knowledge. Although the …