Network Inversion and Its Applications

TL;DR

This paper introduces an effective network inversion method using a conditioned generator with diversity-promoting regularizations, enhancing interpretability and reliability of neural networks in critical applications.

Contribution

The paper proposes a novel network inversion technique employing a conditioned generator with feature orthogonality regularization, improving input reconstruction diversity and interpretability.

Findings

Enhanced input reconstruction diversity through feature orthogonality.

Improved interpretability and trustworthiness of neural networks.

Applications demonstrated in interpretability, out-of-distribution detection, and data reconstruction.

Abstract

Neural networks have emerged as powerful tools across various applications, yet their decision-making process often remains opaque, leading to them being perceived as "black boxes." This opacity raises concerns about their interpretability and reliability, especially in safety-critical scenarios. Network inversion techniques offer a solution by allowing us to peek inside these black boxes, revealing the features and patterns learned by the networks behind their decision-making processes and thereby provide valuable insights into how neural networks arrive at their conclusions, making them more interpretable and trustworthy. This paper presents a simple yet effective approach to network inversion using a meticulously conditioned generator that learns the data distribution in the input space of the trained neural network, enabling the reconstruction of inputs that would most likely lead to the desired outputs. To capture the diversity in the input space for a given output, instead of simply revealing the conditioning labels to the generator, we encode the conditioning label information into vectors and intermediate matrices and further minimize the cosine similarity between features of the generated images. Additionally, we incorporate feature orthogonality as a regularization term to boost image diversity which penalises the deviations of the Gram matrix of the features from the identity matrix, ensuring orthogonality and promoting distinct, non-redundant representations for each label. The paper concludes by exploring immediate applications of the proposed network inversion approach in interpretability, out-of-distribution detection, and training data reconstruction.