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/.
Invertible Neural Networks for Understanding Semantics of Invariances of CNN Representations
Deep Neural Networks and Data for Automated Driving ; Kapitel : 7 ; 197-224
18.06.2022
28 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Invertible Neural Networks for Airfoil Design
AIAA | 2022
|Novel Neural Network Models for Computing Homothetic Invariances: An Image Algebra Notation
British Library Online Contents | 1997
|