Search Results for author: Joseph Paul Cohen

Found 49 papers, 38 papers with code

XTreePath: A generalization of XPath to handle real world structural variation

1 code implementation6 May 2015 Joseph Paul Cohen, Wei Ding, Abraham Bagherjeiran

We propose the XTreePath annotation method to captures contextual node information from the training DOM.

Crater Detection via Convolutional Neural Networks

1 code implementation5 Jan 2016 Joseph Paul Cohen, Henry Z. Lo, Ting-ting Lu, Wei Ding

The power of CNNs is that they can learn image filters which generate features for high accuracy classification.

General Classification

RandomOut: Using a convolutional gradient norm to rescue convolutional filters

1 code implementation18 Feb 2016 Joseph Paul Cohen, Henry Z. Lo, Wei Ding

We propose to evaluate and replace specific convolutional filters that have little impact on the prediction.

Rapid building detection using machine learning

no code implementations14 Mar 2016 Joseph Paul Cohen, Wei Ding, Caitlin Kuhlman, Aijun Chen, Liping Di

This work describes algorithms for performing discrete object detection, specifically in the case of buildings, where usually only low quality RGB-only geospatial reflective imagery is available.

BIG-bench Machine Learning Classification +3

ShortScience.org - Reproducing Intuition

1 code implementation20 Jul 2017 Joseph Paul Cohen, Henry Z. Lo

We present ShortScience. org, a platform for post-publication discussion of research papers.

Digital Libraries

GibbsNet: Iterative Adversarial Inference for Deep Graphical Models

no code implementations NeurIPS 2017 Alex Lamb, Devon Hjelm, Yaroslav Ganin, Joseph Paul Cohen, Aaron Courville, Yoshua Bengio

Directed latent variable models that formulate the joint distribution as $p(x, z) = p(z) p(x \mid z)$ have the advantage of fast and exact sampling.

Attribute

Distribution Matching Losses Can Hallucinate Features in Medical Image Translation

1 code implementation22 May 2018 Joseph Paul Cohen, Margaux Luck, Sina Honari

When the output of an algorithm is a transformed image there are uncertainties whether all known and unknown class labels have been preserved or changed.

Image Generation Translation

Learning to rank for censored survival data

1 code implementation6 Jun 2018 Margaux Luck, Tristan Sylvain, Joseph Paul Cohen, Heloise Cardinal, Andrea Lodi, Yoshua Bengio

Survival analysis is a type of semi-supervised ranking task where the target output (the survival time) is often right-censored.

Learning-To-Rank Survival Analysis

Towards Gene Expression Convolutions using Gene Interaction Graphs

1 code implementation18 Jun 2018 Francis Dutil, Joseph Paul Cohen, Martin Weiss, Georgy Derevyanko, Yoshua Bengio

We find this approach provides an advantage for particular tasks in a low data regime but is very dependent on the quality of the graph used.

Towards the Latent Transcriptome

1 code implementation8 Oct 2018 Assya Trofimov, Francis Dutil, Claude Perreault, Sebastien Lemieux, Yoshua Bengio, Joseph Paul Cohen

In this work we propose a method to compute continuous embeddings for kmers from raw RNA-seq data, without the need for alignment to a reference genome.

Chester: A Web Delivered Locally Computed Chest X-Ray Disease Prediction System

1 code implementation MIDL 2019 Joseph Paul Cohen, Paul Bertin, Vincent Frappier

In order to bridge the gap between Deep Learning researchers and medical professionals we develop a very accessible free prototype system which can be used by medical professionals to understand the reality of Deep Learning tools for chest X-ray diagnostics.

Disease Prediction Out-of-Distribution Detection

GradMask: Reduce Overfitting by Regularizing Saliency

no code implementations16 Apr 2019 Becks Simpson, Francis Dutil, Yoshua Bengio, Joseph Paul Cohen

With too few samples or too many model parameters, overfitting can inhibit the ability to generalise predictions to new data.

Lesion Segmentation

Do Lateral Views Help Automated Chest X-ray Predictions?

1 code implementation17 Apr 2019 Hadrien Bertrand, Mohammad Hashir, Joseph Paul Cohen

Most convolutional neural networks in chest radiology use only the frontal posteroanterior (PA) view to make a prediction.

Torchmeta: A Meta-Learning library for PyTorch

5 code implementations14 Sep 2019 Tristan Deleu, Tobias Würfl, Mandana Samiei, Joseph Paul Cohen, Yoshua Bengio

The constant introduction of standardized benchmarks in the literature has helped accelerating the recent advances in meta-learning research.

Meta-Learning

On summarized validation curves and generalization

no code implementations25 Sep 2019 Mohammad Hashir, Yoshua Bengio, Joseph Paul Cohen

The validation curve is widely used for model selection and hyper-parameter search with the curve usually summarized over all the training tasks.

Model Selection

{COMPANYNAME}11K: An Unsupervised Representation Learning Dataset for Arrhythmia Subtype Discovery

no code implementations25 Sep 2019 Shawn Tan, Guillaume Androz, Ahmad Chamseddine, Pierre Fecteau, Aaron Courville, Yoshua Bengio, Joseph Paul Cohen

We release the largest public ECG dataset of continuous raw signals for representation learning containing over 11k patients and 2 billion labelled beats.

Clustering Representation Learning

Underwhelming Generalization Improvements From Controlling Feature Attribution

no code implementations25 Sep 2019 Joseph D Viviano, Becks Simpson, Francis Dutil, Yoshua Bengio, Joseph Paul Cohen

We describe a simple method for taking advantage of such auxiliary labels, by training networks to ignore the distracting features which may be extracted outside of the region of interest, on the training images for which such masks are available.

Saliency is a Possible Red Herring When Diagnosing Poor Generalization

1 code implementation ICLR 2021 Joseph D. Viviano, Becks Simpson, Francis Dutil, Yoshua Bengio, Joseph Paul Cohen

In some prediction tasks, such as for medical images, one may have some images with masks drawn by a human expert, indicating a region of the image containing relevant information to make the prediction.

General Classification

Deep Semantic Segmentation of Natural and Medical Images: A Review

no code implementations16 Oct 2019 Saeid Asgari Taghanaki, Kumar Abhishek, Joseph Paul Cohen, Julien Cohen-Adad, Ghassan Hamarneh

The semantic image segmentation task consists of classifying each pixel of an image into an instance, where each instance corresponds to a class.

Image Segmentation Medical Image Segmentation +3

The TCGA Meta-Dataset Clinical Benchmark

1 code implementation18 Oct 2019 Mandana Samiei, Tobias Würfl, Tristan Deleu, Martin Weiss, Francis Dutil, Thomas Fevens, Geneviève Boucher, Sebastien Lemieux, Joseph Paul Cohen

Machine learning is bringing a paradigm shift to healthcare by changing the process of disease diagnosis and prognosis in clinics and hospitals.

Decision Making

Icentia11K: An Unsupervised Representation Learning Dataset for Arrhythmia Subtype Discovery

1 code implementation21 Oct 2019 Shawn Tan, Guillaume Androz, Ahmad Chamseddine, Pierre Fecteau, Aaron Courville, Yoshua Bengio, Joseph Paul Cohen

We release the largest public ECG dataset of continuous raw signals for representation learning containing 11 thousand patients and 2 billion labelled beats.

Clustering Representation Learning

Is graph-based feature selection of genes better than random?

1 code implementation21 Oct 2019 Mohammad Hashir, Paul Bertin, Martin Weiss, Vincent Frappier, Theodore J. Perkins, Geneviève Boucher, Joseph Paul Cohen

Gene interaction graphs aim to capture various relationships between genes and represent decades of biology research.

feature selection

On the limits of cross-domain generalization in automated X-ray prediction

9 code implementations MIDL 2019 Joseph Paul Cohen, Mohammad Hashir, Rupert Brooks, Hadrien Bertrand

This large scale study focuses on quantifying what X-rays diagnostic prediction tasks generalize well across multiple different datasets.

Domain Generalization

Quantifying the Value of Lateral Views in Deep Learning for Chest X-rays

1 code implementation MIDL 2019 Mohammad Hashir, Hadrien Bertrand, Joseph Paul Cohen

PadChest is a large-scale chest X-ray dataset that has almost 200 labels and multiple views available.

Revisiting Training Strategies and Generalization Performance in Deep Metric Learning

8 code implementations ICML 2020 Karsten Roth, Timo Milbich, Samarth Sinha, Prateek Gupta, Björn Ommer, Joseph Paul Cohen

Deep Metric Learning (DML) is arguably one of the most influential lines of research for learning visual similarities with many proposed approaches every year.

Metric Learning

Spine intervertebral disc labeling using a fully convolutional redundant counting model

1 code implementation MIDL 2019 Lucas Rouhier, Francisco Perdigon Romero, Joseph Paul Cohen, Julien Cohen-Adad

Labeling intervertebral discs is relevant as it notably enables clinicians to understand the relationship between a patient's symptoms (pain, paralysis) and the exact level of spinal cord injury.

COVID-19 Image Data Collection

13 code implementations25 Mar 2020 Joseph Paul Cohen, Paul Morrison, Lan Dao

This paper describes the initial COVID-19 open image data collection.

COVID-19 Diagnosis

COVID-19 Image Data Collection: Prospective Predictions Are the Future

6 code implementations22 Jun 2020 Joseph Paul Cohen, Paul Morrison, Lan Dao, Karsten Roth, Tim Q Duong, Marzyeh Ghassemi

This dataset currently contains hundreds of frontal view X-rays and is the largest public resource for COVID-19 image and prognostic data, making it a necessary resource to develop and evaluate tools to aid in the treatment of COVID-19.

Management

Uniformizing Techniques to Process CT scans with 3D CNNs for Tuberculosis Prediction

3 code implementations26 Jul 2020 Hasib Zunair, Aimon Rahman, Nabeel Mohammed, Joseph Paul Cohen

A common approach to medical image analysis on volumetric data uses deep 2D convolutional neural networks (CNNs).

Binary Classification

S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learning

1 code implementation17 Sep 2020 Karsten Roth, Timo Milbich, Björn Ommer, Joseph Paul Cohen, Marzyeh Ghassemi

Deep Metric Learning (DML) provides a crucial tool for visual similarity and zero-shot applications by learning generalizing embedding spaces, although recent work in DML has shown strong performance saturation across training objectives.

Ranked #10 on Metric Learning on CARS196 (using extra training data)

Knowledge Distillation Metric Learning +1

ivadomed: A Medical Imaging Deep Learning Toolbox

1 code implementation20 Oct 2020 Charley Gros, Andreanne Lemay, Olivier Vincent, Lucas Rouhier, Anthime Bucquet, Joseph Paul Cohen, Julien Cohen-Adad

ivadomed is an open-source Python package for designing, end-to-end training, and evaluating deep learning models applied to medical imaging data.

object-detection Object Detection +1

Gifsplanation via Latent Shift: A Simple Autoencoder Approach to Counterfactual Generation for Chest X-rays

2 code implementations18 Feb 2021 Joseph Paul Cohen, Rupert Brooks, Sovann En, Evan Zucker, Anuj Pareek, Matthew P. Lungren, Akshay Chaudhari

We also found that the Latent Shift explanation allows a user to have more confidence in true positive predictions compared to traditional approaches (0. 15$\pm$0. 95 in a 5 point scale with p=0. 01) with only a small increase in false positive predictions (0. 04$\pm$1. 06 with p=0. 57).

counterfactual

CheXstray: Real-time Multi-Modal Data Concordance for Drift Detection in Medical Imaging AI

1 code implementation6 Feb 2022 Arjun Soin, Jameson Merkow, Jin Long, Joseph Paul Cohen, Smitha Saligrama, Stephen Kaiser, Steven Borg, Ivan Tarapov, Matthew P Lungren

We use the CheXpert and PadChest public datasets to build and test a medical imaging AI drift monitoring workflow to track data and model drift without contemporaneous ground truth.

Identifying Spurious Correlations using Counterfactual Alignment

1 code implementation1 Dec 2023 Joseph Paul Cohen, Louis Blankemeier, Akshay Chaudhari

We propose the counterfactual alignment method to detect and explore spurious correlations of black box classifiers.

Attribute counterfactual

CheXagent: Towards a Foundation Model for Chest X-Ray Interpretation

no code implementations22 Jan 2024 Zhihong Chen, Maya Varma, Jean-Benoit Delbrouck, Magdalini Paschali, Louis Blankemeier, Dave Van Veen, Jeya Maria Jose Valanarasu, Alaa Youssef, Joseph Paul Cohen, Eduardo Pontes Reis, Emily B. Tsai, Andrew Johnston, Cameron Olsen, Tanishq Mathew Abraham, Sergios Gatidis, Akshay S. Chaudhari, Curtis Langlotz

However, developing FMs that can accurately interpret CXRs is challenging due to the (1) limited availability of large-scale vision-language datasets in the medical image domain, (2) lack of vision and language encoders that can capture the complexities of medical data, and (3) absence of evaluation frameworks for benchmarking the abilities of FMs on CXR interpretation.

Benchmarking Fairness +2

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