Search Results for author: Kevin Smith

Found 17 papers, 10 papers with code

PSL is Dead. Long Live PSL

no code implementations27 May 2022 Kevin Smith, Hai Lin, Praveen Tiwari, Marjorie Sayer, Claudionor Coelho

In this paper, we show that by merging machine learning techniques with PSL monitors, we can extend PSL to work on continuous domains.

Anomaly Detection

CSAW-M: An Ordinal Classification Dataset for Benchmarking Mammographic Masking of Cancer

2 code implementations2 Dec 2021 Moein Sorkhei, Yue Liu, Hossein Azizpour, Edward Azavedo, Karin Dembrower, Dimitra Ntoula, Athanasios Zouzos, Fredrik Strand, Kevin Smith

Interval and large invasive breast cancers, which are associated with worse prognosis than other cancers, are usually detected at a late stage due to false negative assessments of screening mammograms.

Conditional De-Identification of 3D Magnetic Resonance Images

no code implementations18 Oct 2021 Lennart Alexander Van der Goten, Tobias Hepp, Zeynep Akata, Kevin Smith

Solutions have been developed to de-identify diagnostic scans by obfuscating or removing parts of the face.

De-identification

Should we Replace CNNs with Transformers for Medical Images?

no code implementations29 Sep 2021 Christos Matsoukas, Johan Fredin Haslum, Moein Sorkhei, Magnus Soderberg, Kevin Smith

Convolutional Neural Networks (CNNs) have reigned for a decade as the de facto approach to automated medical image diagnosis, pushing the state-of-the-art in classification, detection and segmentation tasks.

Is it Time to Replace CNNs with Transformers for Medical Images?

1 code implementation20 Aug 2021 Christos Matsoukas, Johan Fredin Haslum, Magnus Söderberg, Kevin Smith

Convolutional Neural Networks (CNNs) have reigned for a decade as the de facto approach to automated medical image diagnosis.

Optimal asymptotic of the $J$ functional with respect to the $d_1$ metric

no code implementations7 Jan 2021 Tamás Darvas, Erin George, Kevin Smith

We obtain sharp inequalities between the large scale asymptotic of the $J$ functional with respect to the $d_1$ metric on the space of Kahler metrics.

Differential Geometry Complex Variables

Adversarial Privacy Preservation in MRI Scans of the Brain

no code implementations1 Jan 2021 Lennart Alexander Van der Goten, Tobias Hepp, Zeynep Akata, Kevin Smith

De-identification of magnetic resonance imagery (MRI) is intrinsically difficult since, even with all metadata removed, a person's face can easily be rendered and matched against a database.

De-identification

Adding Seemingly Uninformative Labels Helps in Low Data Regimes

2 code implementations ICML 2020 Christos Matsoukas, Albert Bou I Hernandez, Yue Liu, Karin Dembrower, Gisele Miranda, Emir Konuk, Johan Fredin Haslum, Athanasios Zouzos, Peter Lindholm, Fredrik Strand, Kevin Smith

Evidence suggests that networks trained on large datasets generalize well not solely because of the numerous training examples, but also class diversity which encourages learning of enriched features.

Tumor Segmentation

Decoupling Inherent Risk and Early Cancer Signs in Image-based Breast Cancer Risk Models

1 code implementation11 Jul 2020 Yue Liu, Hossein Azizpour, Fredrik Strand, Kevin Smith

With this in mind, we trained networks using three different criteria to select the positive training data (i. e. images from patients that will develop cancer): an inherent risk model trained on images with no visible signs of cancer, a cancer signs model trained on images containing cancer or early signs of cancer, and a conflated model trained on all images from patients with a cancer diagnosis.

Decision Making

Modeling Expectation Violation in Intuitive Physics with Coarse Probabilistic Object Representations

1 code implementation NeurIPS 2019 Kevin Smith, Lingjie Mei, Shunyu Yao, Jiajun Wu, Elizabeth Spelke, Josh Tenenbaum, Tomer Ullman

We also present a new test set for measuring violations of physical expectations, using a range of scenarios derived from developmental psychology.

Scene Understanding

An empirical study of the relation between network architecture and complexity

no code implementations11 Nov 2019 Emir Konuk, Kevin Smith

In this preregistration submission, we propose an empirical study of how networks handle changes in complexity of the data.

Image Classification

End-to-End Differentiable Physics for Learning and Control

1 code implementation NeurIPS 2018 Filipe de Avila Belbute-Peres, Kevin Smith, Kelsey Allen, Josh Tenenbaum, J. Zico Kolter

We present a differentiable physics engine that can be integrated as a module in deep neural networks for end-to-end learning.

Bayesian Uncertainty Estimation for Batch Normalized Deep Networks

4 code implementations18 Feb 2018 Mattias Teye, Hossein Azizpour, Kevin Smith

We show that training a deep network using batch normalization is equivalent to approximate inference in Bayesian models.

Cannot find the paper you are looking for? You can Submit a new open access paper.