si4onnx: A Python package for Selective Inference in Deep Learning Models

TL;DR

si4onnx is a Python package that facilitates statistically rigorous selective inference in deep learning models, enabling hypothesis testing with controlled error rates for interpretability and reliability.

Contribution

The paper introduces si4onnx, a novel Python package that integrates selective inference techniques into deep learning workflows for the first time.

Findings

Enables hypothesis testing with controlled type I error in deep learning models

Compatible with PyTorch and TensorFlow frameworks

Improves reliability of interpretability methods like CAM and VAE reconstructions

Abstract

In this paper, we introduce si4onnx, a package for performing selective inference on deep learning models. Techniques such as CAM in XAI and reconstruction-based anomaly detection using VAE can be interpreted as methods for identifying significant regions within input images. However, the identified regions may not always carry meaningful significance. Therefore, evaluating the statistical significance of these regions represents a crucial challenge in establishing the reliability of AI systems. si4onnx is a Python package that enables straightforward implementation of hypothesis testing with controlled type I error rates through selective inference. It is compatible with deep learning models constructed using common frameworks such as PyTorch and TensorFlow.