⌘+K

Pulse Explore Communities Researchers Journals

Home Communities Explore

April 19, 2021Proceedings of the Northern Lights Deep Learning WorkshopOpen Access

Robust Deep Interpretable Features for Binary Image Classification

Robert Hu Dino Sejdinović

View Full Paper

Ask AI

Bookmark

Share

Ask about this paper

Answers are grounded in this paper and cite their sources.

Ask your own question…

Abstract

The problem of interpretability for binary image classification is considered through the lens of kernel two-sample tests and generative modeling. A feature extraction framework coined Deep Interpretable Features (DIF) is developed, which is used in combination with IntroVAE, a generative model capable of high-resolution image synthesis. Experimental results on a variety of datasets, including COVID-19 chest x-rays demonstrate the benefits of combining deep generative models with the ideas from kernel-based hypothesis testing in moving towards more robust interpretable deep generative models.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Hu et al. (2021) studied this question.

synapsesocial.com/papers/6a1074335725bbd5cc61087b https://doi.org/10.7557/18.5708

View Full Paper

Ask AI

Bookmark

Share

Keep reading

Synapse has enriched 5 related papers. Consider them for comparative context:

1A contrastive learning approach for individual re-identification in a wild fish populationProceedings of the Northern Lights Deep Learning Workshop · 2023
2Multi-modal data generation with a deep metric variational autoencoderProceedings of the Northern Lights Deep Learning Workshop · 2023
3PLM-AS: Pre-trained Language Models Augmented with Scanpaths for Sentiment ClassificationProceedings of the Northern Lights Deep Learning Workshop · 2023
4Automatic Consistency Checking of Table and Text in Financial DocumentsProceedings of the Northern Lights Deep Learning Workshop · 2023
5Learning to solve arithmetic problems with a virtual abacusProceedings of the Northern Lights Deep Learning Workshop · 2023

Simplifying Clustering with Graph Neural NetworksProceedings of the Northern Lights Deep Learning Workshop · 2023
Solving Nonlinear Conservation Laws of Partial Differential Equations Using Graph Neural NetworksProceedings of the Northern Lights Deep Learning Workshop · 2023
Robin Pre-Training for the Deep Ritz MethodProceedings of the Northern Lights Deep Learning Workshop · 2023
Evaluating current state of monocular 3D pose models for golfProceedings of the Northern Lights Deep Learning Workshop · 2023
Småprat: DialoGPT for Natural Language Generation of Swedish Dialogue by Transfer LearningProceedings of the Northern Lights Deep Learning Workshop · 2022

More from Proceedings of the Northern Lights Deep Learning Workshop

More from University of Oxford