si4onnx: A Python package for Selective Inference in Deep Learning Models
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Anomaly DetectionDeep LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Seg-metrics: a Python package to compute segmentation metrics
In response to a concerning trend of selectively emphasizing metrics in medical image segmentation (MIS) studies, we introduce \texttt{seg-metrics}, an open-source Python package for standardized MIS model evaluation. Un…
Image SegmentationMedical Image SegmentationSemantic SegmentationONNXExplainer: an ONNX Based Generic Framework to Explain Neural Networks Using Shapley Values
Understanding why a neural network model makes certain decisions can be as important as the inference performance. Various methods have been proposed to help practitioners explain the prediction of a neural network model…
ESPnet-ONNX: Bridging a Gap Between Research and Production
In the field of deep learning, researchers often focus on inventing novel neural network models and improving benchmarks. In contrast, application developers are interested in making models suitable for actual products, …
Spoken Language UnderstandingCausalML: Python Package for Causal Machine Learning
CausalML is a Python implementation of algorithms related to causal inference and machine learning. Algorithms combining causal inference and machine learning have been a trending topic in recent years. This package trie…
BIG-bench Machine LearningCausal InferenceQRMine: A python package for triangulation in Grounded Theory
Grounded theory (GT) is a qualitative research method for building theory grounded in data. GT uses textual and numeric data and follows various stages of coding or tagging data for sense-making, such as open coding and …