7 papers · 1 filter
Discovery and Spatial Characterisation of Multiple Shortcut Groups for Auditing Vision Model Bias
Akshit Achara, Vishnunarayan Manickam, Thomas Day +3
Deep learning models trained on datasets with spurious correlations can achieve high average accuracy whilst relying on shortcut features that do not generalise out of distribution…
EquiSteer: Cross-Attention Steering Towards a Fairer Text-Guided Image Generation
Tatiana Gaintseva, Akshit Achara, Gregory Slabaugh +2
Text-to-image diffusion models power everyday creative tasks, but they still reproduce the demographic biases in their training data. On common prompts such as ``a photo of a nurse…
Right Regions, Wrong Labels: Semantic Label Flips in Segmentation under Correlation Shift
Akshit Achara, Yovin Yahathugoda, Nick Byrne +4
The robustness of machine learning models can be compromised by spurious correlations between non-causal features in the input data and target labels. A common way to test for such…
Understanding Sources of Demographic Predictability in Brain MRI via Disentangling Anatomy and Contrast
Mehmet Yigit Avci, Akshit Achara, Andrew King +1
Demographic attributes can be predicted from medical images, raising concerns about bias in clinical AI systems. In X-ray imaging, acquisition characteristics have been shown to co…
Localising Shortcut Learning in Pixel Space via Ordinal Scoring Correlations for Attribution Representations (OSCAR)
Akshit Achara, Peter Triantafillou, Esther Puyol-Antón +2
Deep neural networks often exploit shortcuts. These are spurious cues which are associated with output labels in the training data but are unrelated to task semantics. When the sho…
Invisible Attributes, Visible Biases: Exploring Demographic Shortcuts in MRI-based Alzheimer's Disease Classification
Akshit Achara, Esther Puyol Anton, Alexander Hammers +1
Magnetic resonance imaging (MRI) is the gold standard for brain imaging. Deep learning (DL) algorithms have been proposed to aid in the diagnosis of diseases such as Alzheimer's di…