paper-with-me

Papers

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

2025-01-29 · Teruyuki Katsuoka, Tomohiro Shiraishi, Daiki Miwa, Shuichi Nishino, Ichiro Takeuchi

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.

📄 PDF Abstract BibTeX arXiv:2501.17415

Code (0)

등록된 구현이 없습니다.

Tasks

Anomaly DetectionDeep Learning

Methods 이 논문이 사용한 방법론

CAM Class activation maps could be used to interpret the prediction decision made by the convolutional neural network (CNN). Image source: [Learning Deep Features for…

Similar Papers 제목 키워드 기반

Seg-metrics: a Python package to compute segmentation metrics

2024-01-12 · Jingnan Jia, Marius Staring, Berend C. Stoel

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 Segmentation

ONNXExplainer: an ONNX Based Generic Framework to Explain Neural Networks Using Shapley Values

2023-09-29 · Yong Zhao, Runxin He, Nicholas Kersting, Can Liu 외

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

2022-09-20 · Masao Someki, Yosuke Higuchi, Tomoki Hayashi, Shinji Watanabe

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 Understanding

CausalML: Python Package for Causal Machine Learning

2020-02-25 · Huigang Chen, Totte Harinen, Jeong-Yoon Lee, Mike Yung 외

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 Inference

QRMine: A python package for triangulation in Grounded Theory

2020-03-30 · Bell Raj Eapen, Norm Archer, Kamran Sartipi

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 …