The vast quantity of information brought by big data as well as the evolving computer
hardware encourages success stories in the machine learning community. In the …

In this paper, we leverage CLIP for zero-shot sketch based image retrieval (ZS-SBIR). We
are largely inspired by recent advances on foundation models and the unparalleled …

Gaussian processes (GPs) provide a framework for Bayesian inference that can offer
principled uncertainty estimates for a large range of problems. For example, if we consider …

We advocate an optimization-centric view of Bayesian inference. Our inspiration is the
representation of Bayes' rule as infinite-dimensional optimization (Csisz´ r, 1975; Donsker …

GPflow is a Gaussian process library that uses TensorFlow for its core computations and
Python for its front end. The distinguishing features of GPflow are that it uses variational …

Variational Bayesian neural networks (BNNs) perform variational inference over weights, but
it is difficult to specify meaningful priors and approximate posteriors in a high-dimensional …

Good sparse approximations are essential for practical inference in Gaussian Processes as
the computational cost of exact methods is prohibitive for large datasets. The Fully …

Excellent variational approximations to Gaussian process posteriors have been developed
which avoid the $\mathcal {O}\left (N^ 3\right) $ scaling with dataset size $ N $. They reduce …

This paper advances the fine-grained sketch-based image retrieval (FG-SBIR) literature by
putting forward a strong baseline that overshoots prior state-of-the art by 11%. This is not via …

We present a practical way of introducing convolutional structure into Gaussian processes,
making them more suited to high-dimensional inputs like images. The main contribution of …