469 citations · 1.6k across the 93 of their papers we have counts for
52 papers · 1 filter
Causal Spatio-Temporal Neural Distance Fields for Counterfactual Cardiac Anatomy
Mathias Lowes, Kurt Butler, Kristine Aavild Sørensen +4
Counterfactual cardiac anatomy can support risk modelling and intervention planning, by predicting how a patient's heart would change under altered clinical conditions. However, cu…
Scaling Generative Foundation Models for Chest Radiography with Rectified Flow Transformers
Fabio De Sousa Ribeiro, Emma A. M. Stanley, Charles Jones +7
We introduce the first generative foundation model for chest radiograph synthesis trained from scratch at the billion-parameter scale. Existing radiographic AI models often suffer…
Why Do Vision Language Models Struggle To Recognize Human Emotions?
Madhav Agarwal, Sotirios A. Tsaftaris, Laura Sevilla-Lara +1
Understanding emotions is a fundamental ability for intelligent systems to be able to interact with humans. Vision-language models (VLMs) have made tremendous progress in the last…
Preventing Shortcut Learning in Medical Image Analysis through Intermediate Layer Knowledge Distillation from Specialist Teachers
Christopher Boland, Sotirios Tsaftaris, Sonia Dahdouh
Deep learning models are prone to learning shortcut solutions to problems using spuriously correlated yet irrelevant features of their training data. In high-risk applications such…
MedVision: Benchmarking Quantitative Medical Image Analysis
Yongcheng Yao, Yongshuo Zong, Raman Dutt +3
Current vision-language models (VLMs) in medicine are primarily designed for categorical question answering (e.g., "Is this normal or abnormal?") or qualitative descriptive tasks.…
Count2Density: Crowd Density Estimation without Location-level Annotations
Mattia Litrico, Feng Chen, Michael Pound +3
Crowd density estimation is a well-known computer vision task aimed at estimating the density distribution of people in an image. The main challenge in this domain is the reliance…
Causal-Adapter: Taming Text-to-Image Diffusion for Faithful Counterfactual Generation
Lei Tong, Zhihua Liu, Chaochao Lu +5
We present Causal-Adapter, a modular framework that adapts frozen text-to-image diffusion backbones for counterfactual image generation. Our method supports causal interventions on…
Causally Steered Diffusion for Automated Video Counterfactual Generation
Nikos Spyrou, Athanasios Vlontzos, Paraskevas Pegios +5
Adapting text-to-image (T2I) latent diffusion models (LDMs) to video editing has shown strong visual fidelity and controllability, but challenges remain in maintaining causal relat…
Anatomy-Grounded Weakly Supervised Prompt Tuning for Chest X-ray Latent Diffusion Models
Konstantinos Vilouras, Ilias Stogiannidis, Junyu Yan +2
Latent Diffusion Models have shown remarkable results in text-guided image synthesis in recent years. In the domain of natural (RGB) images, recent works have shown that such model…
CheXGenBench: A Unified Benchmark For Fidelity, Privacy and Utility of Synthetic Chest Radiographs
Raman Dutt, Pedro Sanchez, Yongchen Yao +3
Structured benchmarks have advanced text-conditional image generation for real-world imagery, however, no such benchmark exists for synthetic radiograph generation. Despite being a…
CRCE: Coreference-Retention Concept Erasure in Text-to-Image Diffusion Models
Yuyang Xue, Edward Moroshko, Feng Chen +3
Text-to-Image diffusion models can produce undesirable content that necessitates concept erasure. However, existing methods struggle with under-erasure, leaving residual traces of…
Unlocking the Potential of Weakly Labeled Data: A Co-Evolutionary Learning Framework for Abnormality Detection and Report Generation
Jinghan Sun, Dong Wei, Zhe Xu +7
Anatomical abnormality detection and report generation of chest X-ray (CXR) are two essential tasks in clinical practice. The former aims at localizing and characterizing cardiopul…
Capacity Control is an Effective Memorization Mitigation Mechanism in Text-Conditional Diffusion Models
Raman Dutt, Pedro Sanchez, Ondrej Bohdal +2
In this work, we present compelling evidence that controlling model capacity during fine-tuning can effectively mitigate memorization in diffusion models. Specifically, we demonstr…
GMT: Guided Mask Transformer for Leaf Instance Segmentation
Feng Chen, Sotirios A. Tsaftaris, Mario Valerio Giuffrida
Leaf instance segmentation is a challenging multi-instance segmentation task, aiming to separate and delineate each leaf in an image of a plant. Accurate segmentation of each leaf…
MemControl: Mitigating Memorization in Diffusion Models via Automated Parameter Selection
Raman Dutt, Ondrej Bohdal, Pedro Sanchez +2
Diffusion models excel in generating images that closely resemble their training data but are also susceptible to data memorization, raising privacy, ethical, and legal concerns, p…
Zero-Shot Medical Phrase Grounding with Off-the-shelf Diffusion Models
Konstantinos Vilouras, Pedro Sanchez, Alison Q. O'Neil +1
Localizing the exact pathological regions in a given medical scan is an important imaging problem that traditionally requires a large amount of bounding box ground truth annotation…
Boosting Few-Shot Learning with Disentangled Self-Supervised Learning and Meta-Learning for Medical Image Classification
Eva Pachetti, Sotirios A. Tsaftaris, Sara Colantonio
Background and objective: Employing deep learning models in critical domains such as medical imaging poses challenges associated with the limited availability of training data. We…
Benchmarking Counterfactual Image Generation
Thomas Melistas, Nikos Spyrou, Nefeli Gkouti +5
Generative AI has revolutionised visual content editing, empowering users to effortlessly modify images and videos. However, not all edits are equal. To perform realistic edits in…
Group Distributionally Robust Knowledge Distillation
Konstantinos Vilouras, Xiao Liu, Pedro Sanchez +2
Knowledge distillation enables fast and effective transfer of features learned from a bigger model to a smaller one. However, distillation objectives are susceptible to sub-populat…
Compositional Representation Learning for Brain Tumour Segmentation
Xiao Liu, Antanas Kascenas, Hannah Watson +2
For brain tumour segmentation, deep learning models can achieve human expert-level performance given a large amount of data and pixel-level annotations. However, the expensive exer…
FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis
Raman Dutt, Ondrej Bohdal, Sotirios A. Tsaftaris +1
Training models with robust group fairness properties is crucial in ethically sensitive application areas such as medical diagnosis. Despite the growing body of work aiming to mini…
Debiasing Counterfactuals In the Presence of Spurious Correlations
Amar Kumar, Nima Fathi, Raghav Mehta +4
Deep learning models can perform well in complex medical imaging classification tasks, even when basing their conclusions on spurious correlations (i.e. confounders), should they b…
Compositionally Equivariant Representation Learning
Xiao Liu, Pedro Sanchez, Spyridon Thermos +2
Deep learning models often need sufficient supervision (i.e. labelled data) in order to be trained effectively. By contrast, humans can swiftly learn to identify important anatomy…
Parameter-Efficient Fine-Tuning for Medical Image Analysis: The Missed Opportunity
Raman Dutt, Linus Ericsson, Pedro Sanchez +2
Foundation models have significantly advanced medical image analysis through the pre-train fine-tune paradigm. Among various fine-tuning algorithms, Parameter-Efficient Fine-Tuning…