5 papers
Causal State-Space Model for Causal Inference: Estimating Longitudinal Individual Treatment Effects
Abisoye Abidakun, Mingjun Zhong, Georgios Leontidis
Estimating counterfactual outcomes over time from longitudinal observational data is central to clinical decision support. Existing methods rely on domain confusion -- adversarial…
The Impact of Semantic Pairs on Self-Supervised Representation Learning
Mohammad Alkhalefi, Georgios Leontidis, Mingjun Zhong
Instance discrimination learns visual representations by treating different augmented views of the same image as positive pairs. While this encourages invariance to handcrafted tra…
Capsule Network Projectors are Equivariant and Invariant Learners
Miles Everett, Aiden Durrant, Mingjun Zhong +1
Learning invariant representations has been the long-standing approach to self-supervised learning. However, recently progress has been made in preserving equivariant properties in…
LeOCLR: Leveraging Original Images for Contrastive Learning of Visual Representations
Mohammad Alkhalefi, Georgios Leontidis, Mingjun Zhong
Contrastive instance discrimination methods outperform supervised learning in downstream tasks such as image classification and object detection. However, these methods rely heavil…
Masked Capsule Autoencoders
Miles Everett, Mingjun Zhong, Georgios Leontidis
We propose Masked Capsule Autoencoders (MCAE), the first Capsule Network that utilises pretraining in a modern self-supervised paradigm, specifically the masked image modelling fra…