@inproceedings{schmalwasser2024exploiting,
    type = {inproceedings},
    key = {schmalwasser2024exploiting},
    title = {Exploiting Text-Image Latent Spaces for the Description of Visual Concepts},
    author = {Laines Schmalwasser and Jakob Gawlikowski and Joachim Denzler and Julia Niebling},
    booktitle = {International Conference on Pattern Recognition (ICPR)},
    year = {2024},
    doi = {},
    groups = {},
    abstract = {Concept Activation Vectors (CAVs) offer insights into neural network decision-making by linking human friendly concepts to the model's internal feature extraction process. However, when a new set of CAVs is discovered, they must still be translated into a human understandable description. For image-based neural networks, this is typically done by visualizing the most relevant images of a CAV, while the determination of the concept is left to humans. In this work, we introduce an approach to aid the interpretation of newly discovered concept sets by suggesting textual descriptions for each CAV. This is done by mapping the most relevant images representing a CAV into a text-image embedding where a joint description of these relevant images can be computed. We propose utilizing the most relevant receptive fields instead of full images encoded. We demonstrate the capabilities of this approach in multiple experiments with and without given CAV labels, showing that the proposed approach provides accurate descriptions for the CAVs and reduces the challenge of concept interpretation.},
    note = {(accepted at ICPR)},
}