paper-with-me

Papers

Gi and Pal Scores: Deep Neural Network Generalization Statistics

2021-04-08 · Yair Schiff, Brian Quanz, Payel Das, Pin-Yu Chen

The field of Deep Learning is rich with empirical evidence of human-like performance on a variety of regression, classification, and control tasks. However, despite these successes, the field lacks strong theoretical error bounds and consistent measures of network generalization and learned invariances. In this work, we introduce two new measures, the Gi-score and Pal-score, that capture a deep neural network's generalization capabilities. Inspired by the Gini coefficient and Palma ratio, measures of income inequality, our statistics are robust measures of a network's invariance to perturbations that accurately predict generalization gaps, i.e., the difference between accuracy on training and test sets.

📄 PDF Abstract BibTeX arXiv:2104.03469

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

Predicting Deep Neural Network Generalization with Perturbation Response Curves

2021-06-09 · NeurIPS 2021 12 · Yair Schiff, Brian Quanz, Payel Das, Pin-Yu Chen

The field of Deep Learning is rich with empirical evidence of human-like performance on a variety of prediction tasks. However, despite these successes, the recent Predicting Generalization in Deep Learning (PGDL) NeurIP…

Risk-based Calibration for Generative Classifiers

2024-09-05 · Aritz Pérez, Carlos Echegoyen, Guzmán Santafé

Generative classifiers are constructed on the basis of a joint probability distribution and are typically learned using closed-form procedures that rely on data statistics and maximize scores related to data fitting. How…

Improving robustness against common corruptions by covariate shift adaptation

2020-06-30 · NeurIPS 2020 12 · Steffen Schneider, Evgenia Rusak, Luisa Eck, Oliver Bringmann 외

Today's state-of-the-art machine vision models are vulnerable to image corruptions like blurring or compression artefacts, limiting their performance in many real-world applications. We here argue that popular benchmarks…

Domain GeneralizationImage ClassificationOut-of-Distribution GeneralizationUnsupervised Domain Adaptation

The Devil is in the Statistics: Mitigating and Exploiting Statistics Difference for Generalizable Semi-supervised Medical Image Segmentation

2024-07-16 · Muyang Qiu, Jian Zhang, Lei Qi, Qian Yu 외

Despite the recent success of domain generalization in medical image segmentation, voxel-wise annotation for all source domains remains a huge burden. Semi-supervised domain generalization has been proposed very recently…

Domain GeneralizationImage SegmentationMedical Image SegmentationPseudo Label+3

On Consistency of Graph-based Semi-supervised Learning

2017-03-17 · Chengan Du, Yunpeng Zhao, Feng Wang

Graph-based semi-supervised learning is one of the most popular methods in machine learning. Some of its theoretical properties such as bounds for the generalization error and the convergence of the graph Laplacian regul…