Towards Explainable Motion Prediction using Heterogeneous Graph Representations

1 code implementation • 7 Dec 2022 • Sandra Carrasco Limeros, Sylwia Majchrowska, Joakim Johnander, Christoffer Petersson, David Fernández Llorca

In this work, we aim to improve the explainability of motion prediction systems by using different approaches.

Autonomous Driving counterfactual +2

Towards trustworthy multi-modal motion prediction: Holistic evaluation and interpretability of outputs

1 code implementation • 28 Oct 2022 • Sandra Carrasco Limeros, Sylwia Majchrowska, Joakim Johnander, Christoffer Petersson, Miguel Ángel Sotelo, David Fernández Llorca

First, we comprehensively analyse the evaluation metrics, identify the main gaps of current benchmarks, and propose a new holistic evaluation framework.

Autonomous Vehicles motion prediction

GAN-based generative modelling for dermatological applications -- comparative study

1 code implementation • 24 Aug 2022 • Sandra Carrasco Limeros, Sylwia Majchrowska, Mohamad Khir Zoubi, Anna Rosén, Juulia Suvilehto, Lisa Sjöblom, Magnus Kjellberg

The lack of sufficiently large open medical databases is one of the biggest challenges in AI-powered healthcare.

The (de)biasing effect of GAN-based augmentation methods on skin lesion images

2 code implementations • 30 Jun 2022 • Agnieszka Mikołajczyk, Sylwia Majchrowska, Sandra Carrasco Limeros

In addition, we examined classification models trained on both real and synthetic data with counterfactual bias explanations.

counterfactual Data Augmentation