1 code implementation • 30 Oct 2023 • Beatrix M. G. Nielsen, Anders Christensen, Andrea Dittadi, Ole Winther
Diffusion models may be viewed as hierarchical variational autoencoders (VAEs) with two improvements: parameter sharing for the conditional distributions in the generative process and efficient computation of the loss as independent terms over the hierarchy.
1 code implementation • ICCV 2023 • Anders Christensen, Massimiliano Mancini, A. Sophia Koepke, Ole Winther, Zeynep Akata
We achieve this with our proposed Image-free Classifier Injection with Semantics (ICIS) that injects classifiers for new, unseen classes into pre-trained classification models in a post-hoc fashion without relying on image data.
1 code implementation • 20 Jul 2023 • Leander Girrbach, Anders Christensen, Ole Winther, Zeynep Akata, A. Sophia Koepke
Whilst this captures useful information for linear classifiers, we find that no relevant spatial structure is present in later layers of deep neural networks, making neural persistence roughly equivalent to the variance of weights.
no code implementations • 6 Oct 2022 • Anders Christensen, Joel Ferguson, Simón Ramírez Amaya
Recent efforts have been very successful in accurately mapping welfare in datasparse regions of the world using satellite imagery and other non-traditional data sources.
1 code implementation • NeurIPS 2020 • Valentin Liévin, Andrea Dittadi, Anders Christensen, Ole Winther
Empirically, for the training of both continuous and discrete generative models, the proposed method yields superior variance reduction, resulting in an SNR for IWAE that increases with $K$ without relying on the reparameterization trick.
1 code implementation • 5 Aug 2020 • Valentin Liévin, Andrea Dittadi, Anders Christensen, Ole Winther
This paper introduces novel results for the score function gradient estimator of the importance weighted variational bound (IWAE).