To tackle increasingly complex tasks, it has become an essential ability of neural networks to learn abstract representations. These task-specific representations and, particularly, the invariances they capture turn neural networks into black-box models that lack interpretability. To open such a black box, it is, therefore, crucial to uncover the different semantic concepts a model has learned as well as those that it has learned to be invariant to. We present an approach based on invertible neural networks (INNs) that (i) recovers the task-specific, learned invariances by disentangling the remaining factor of variation in the data and that (ii) invertibly transforms these recovered invariances combined with the model representation into an equally expressive one with accessible semantic concepts. As a consequence, neural network representations become understandable by providing the means to (i) expose their semantic meaning, (ii) semantically modify a representation, and (iii) visualize individual learned semantic concepts and invariances. Our invertible approach significantly extends the abilities to understand black-box models by enabling post hoc interpretations of state-of-the-art networks without compromising their performance. Our implementation is available at https://compvis.github.io/invariances/.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Invertible Neural Networks for Understanding Semantics of Invariances of CNN Representations


    Beteiligte:
    Fingscheidt, Tim (Herausgeber:in) / Gottschalk, Hanno (Herausgeber:in) / Houben, Sebastian (Herausgeber:in) / Rombach, Robin (Autor:in) / Esser, Patrick (Autor:in) / Blattmann, Andreas (Autor:in) / Ommer, Björn (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    18.06.2022


    Format / Umfang :

    28 pages




    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Invertible Neural Networks for Airfoil Design

    Glaws, Andrew / King, Ryan N. / Vijayakumar, Ganesh et al. | AIAA | 2022


    Novel Neural Network Models for Computing Homothetic Invariances: An Image Algebra Notation

    Paz, C. / Araujo, S. | British Library Online Contents | 1997


    Regularizing invertible neural networks for airfoil design through dimension reduction

    Glaws, Andrew / Hokanson, Jeffrey / King, Ryan et al. | AIAA | 2022


    Regularizing Invertible Neural Networks for Airfoil Design Through Dimension Reduction

    Glaws, Andrew / Hokanson, Jeffrey / King, Ryan et al. | TIBKAT | 2022


    Inverse Design of Thermodynamic Systems Using Conditional Invertible Neural Networks

    Zhang, Zhanpan / Tsilifis, Panagiotis / Shah, Tapan et al. | AIAA | 2025