Network Inversion of Convolutional Neural Nets

TL;DR

This paper introduces a method for network inversion in convolutional neural networks using a conditioned generator, enhancing interpretability by reconstructing likely inputs for given outputs.

Contribution

It proposes a novel approach with a conditioned generator that learns data distribution and encodes label information to improve input reconstruction for interpretability.

Findings

Effective reconstruction of inputs from neural network outputs

Enhanced diversity in generated inputs

Improved interpretability of neural network decision processes

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.