3 citations · 3 across the 4 of their papers we have counts for
7 papers
Repurposing Obsolete Representations for Post-Deployment Adaptation
Daniel Bethell, Charmaine Barker, Simos Gerasimou
Deep neural networks are increasingly deployed in long-lived systems, where task requirements may change after training. In such settings, part of the original output space may bec…
Localisation-Aware Uncertainty for Pretrained Object Detection
Charmaine Barker, Daniel Bethell, Simos Gerasimou
Reliable uncertainty estimation is essential for deploying object detectors when distribution/covariate shift and adversarial attacks may occur. Existing approaches often require d…
Robust Evidential Learning Through Latent Consistency
Charmaine Barker, Daniel Bethell, Simos Gerasimou
Reliable uncertainty quantification is essential for deploying deep learning models in high-stakes settings, where out-of-distribution and adversarial inputs can induce confident b…
Guided Uncertainty Learning Using a Post-Hoc Evidential Meta-Model
Charmaine Barker, Daniel Bethell, Simos Gerasimou
Reliable uncertainty quantification remains a major obstacle to the deployment of deep learning models under distributional shift. Existing post-hoc approaches that retrofit pretra…
Robust Adversarial Quantification via Conflict-Aware Evidential Deep Learning
Charmaine Barker, Daniel Bethell, Simos Gerasimou
Reliability of deep learning models is critical for deployment in high-stakes applications, where out-of-distribution or adversarial inputs may lead to detrimental outcomes. Eviden…
Learning Fairer Representations with FairVIC
Charmaine Barker, Daniel Bethell, Dimitar Kazakov
Mitigating bias in automated decision-making systems, particularly in deep learning models, is a critical challenge due to nuanced definitions of fairness, dataset-specific biases,…
Mitigating Bias in Text Classification via Prompt-Based Text Transformation
Charmaine Barker, Dimitar Kazakov
The presence of specific linguistic signals particular to a certain sub-group can become highly salient to language models during training. In automated decision-making settings, t…