6 papers
Steering Optimisation Trajectories in Diffusion Representation Learning
Rajat Rasal, Avinash Kori, Tian Xia +1
We study why diffusion autoencoders can achieve similar image quality while learning substantially different latent structures. We trace this behaviour to optimisation dynamics; we…
Factored Classifier-Free Guidance
Tian Xia, Fabio De Sousa Ribeiro, Rajat R Rasal +3
Counterfactual generation aims to simulate realistic hypothetical outcomes under causal interventions. Diffusion models have emerged as a powerful tool for this task, combining DDI…
Positional Segmentor-Guided Counterfactual Fine-Tuning for Spatially Localized Image Synthesis
Tian Xia, Matthew Sinclair, Andreas Schuh +8
Counterfactual image generation enables controlled data augmentation, bias mitigation, and disease modeling. However, existing methods guided by external classifiers or regressors…
Causal Representation Learning with Observational Grouping for CXR Classification
Rajat Rasal, Avinash Kori, Ben Glocker
Identifiable causal representation learning seeks to uncover the true causal relationships underlying a data generation process. In medical imaging, this presents opportunities to…
Segmentor-Guided Counterfactual Fine-Tuning for Locally Coherent and Targeted Image Synthesis
Tian Xia, Matthew Sinclair, Andreas Schuh +8
Counterfactual image generation is a powerful tool for augmenting training data, de-biasing datasets, and modeling disease. Current approaches rely on external classifiers or regre…
Diffusion Counterfactual Generation with Semantic Abduction
Rajat Rasal, Avinash Kori, Fabio De Sousa Ribeiro +2
Counterfactual image generation presents significant challenges, including preserving identity, maintaining perceptual quality, and ensuring faithfulness to an underlying causal mo…