Abstract Representation learning has significantly driven the field to develop pretrained
models that can act as a valuable starting point when transferring to new datasets. With the …

Contrastively trained encoders have recently been proven to invert the data-generating
process: they encode each input, eg, an image, into the true latent vector that generated the …

Generalizable medical image segmentation enables models to generalize to unseen target
domains under domain shift issues. Recent progress demonstrates that the shape of the …

Accurate uncertainty estimation is vital to trustworthy machine learning, yet uncertainties
typically have to be learned for each task anew. This work introduces the first pretrained …

Recently, hyperspherical embeddings have established themselves as a dominant
technique for face and voice recognition. Specifically, Euclidean space vector embeddings …

In recent years, self-supervised learning has played a pivotal role in advancing machine
learning by allowing models to acquire meaningful representations from unlabeled data. An …

The performance of modern deep learning-based systems dramatically depends on the
quality of input objects. For example, face recognition quality is lower for blurry or corrupted …

Uncertainty quantification is a key pillar of trustworthy machine learning. It enables safe
reactions under unsafe inputs, like predicting only when the machine learning model detects …

In most re-identification approaches, embedding vectors are compared to identify the best
match for a given query. However, this comparison does not take into account whether the …

Accurately estimating image quality and model robustness improvement are critical
challenges in unconstrained face recognition, which can be addressed through uncertainty …