71 citations · 604 across the 67 of their papers we have counts for
5 papers · 2 filters
Group Equivariant Subsampling
Jin Xu, Hyunjik Kim, Tom Rainforth +1
Subsampling is used in convolutional neural networks (CNNs) in the form of pooling or strided convolutions, to reduce the spatial dimensions of feature maps and to allow the recept…
Learning Multimodal VAEs through Mutual Supervision
Tom Joy, Yuge Shi, Philip H. S. Torr +3
Multimodal VAEs seek to model the joint distribution over heterogeneous data (e.g.\ vision, language), whilst also capturing a shared representation across such modalities. Prior w…
Test Distribution-Aware Active Learning: A Principled Approach Against Distribution Shift and Outliers
Andreas Kirsch, Tom Rainforth, Yarin Gal
Expanding on MacKay (1992), we argue that conventional model-based methods for active learning - like BALD - have a fundamental shortfall: they fail to directly account for the tes…
Expectation Programming: Adapting Probabilistic Programming Systems to Estimate Expectations Efficiently
Tim Reichelt, Adam Goliński, Luke Ong +1
We show that the standard computational pipeline of probabilistic programming systems (PPSs) can be inefficient for estimating expectations and introduce the concept of expectation…
Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
Jannik Kossen, Neil Band, Clare Lyle +3
We challenge a common assumption underlying most supervised deep learning: that a model makes a prediction depending only on its parameters and the features of a single input. To t…