1 code implementation • 4 Sep 2023 • Meghal Dani, Isabel Rio-Torto, Stephan Alaniz, Zeynep Akata
We demonstrate that DeViL generates textual descriptions relevant to the image content on CC3M surpassing previous lightweight captioning models and attribution maps uncovering the learned concepts of the vision backbone.
1 code implementation • NeurIPS 2023 • Leonard Salewski, Stephan Alaniz, Isabel Rio-Torto, Eric Schulz, Zeynep Akata
These findings demonstrate that LLMs are capable of taking on diverse roles and that this in-context impersonation can be used to uncover their hidden strengths and biases.
1 code implementation • 26 Apr 2022 • Tiago Gonçalves, Isabel Rio-Torto, Luís F. Teixeira, Jaime S. Cardoso
This paper concludes with a critical analysis of the claims and potentialities presented in the literature about attention mechanisms and proposes future research lines in medical applications that may benefit from these frameworks.
1 code implementation • Pattern Recognition Letters 2020 • Isabel Rio-Torto, Kelwin Fernandes, Luís Teixeira
The model is trained end-to-end, with the classifier taking as input an image and the explainer’s resulting explanation, thus allowing for the classifier to focus on the relevant areas of such explanation.