Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Hossein Azizpour

Hossein Azizpour

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


Jul 14, 2020
Yue Liu, Hossein Azizpour, Fredrik Strand, Kevin Smith

Figure 1 for Decoupling Inherent Risk and Early Cancer Signs in Image-based Breast Cancer Risk Models
Figure 2 for Decoupling Inherent Risk and Early Cancer Signs in Image-based Breast Cancer Risk Models
Figure 3 for Decoupling Inherent Risk and Early Cancer Signs in Image-based Breast Cancer Risk Models
Figure 4 for Decoupling Inherent Risk and Early Cancer Signs in Image-based Breast Cancer Risk Models
* Medical Image Computing and Computer Assisted Interventions 2020 
  Access Paper or Ask Questions

Explanation-based Weakly-supervised Learning of Visual Relations with Graph Networks


Jun 16, 2020
Federico Baldassarre, Kevin Smith, Josephine Sullivan, Hossein Azizpour

Figure 1 for Explanation-based Weakly-supervised Learning of Visual Relations with Graph Networks
Figure 2 for Explanation-based Weakly-supervised Learning of Visual Relations with Graph Networks
Figure 3 for Explanation-based Weakly-supervised Learning of Visual Relations with Graph Networks
Figure 4 for Explanation-based Weakly-supervised Learning of Visual Relations with Graph Networks

  Access Paper or Ask Questions

Recurrent neural networks and Koopman-based frameworks for temporal predictions in turbulence


May 01, 2020
Hamidreza Eivazi, Luca Guastoni, Philipp Schlatter, Hossein Azizpour, Ricardo Vinuesa

Figure 1 for Recurrent neural networks and Koopman-based frameworks for temporal predictions in turbulence
Figure 2 for Recurrent neural networks and Koopman-based frameworks for temporal predictions in turbulence
Figure 3 for Recurrent neural networks and Koopman-based frameworks for temporal predictions in turbulence
Figure 4 for Recurrent neural networks and Koopman-based frameworks for temporal predictions in turbulence
* arXiv admin note: significant text overlap with arXiv:2002.01222 
  Access Paper or Ask Questions

Hyperplane Arrangements of Trained ConvNets Are Biased


Mar 17, 2020
Matteo Gamba, Stefan Carlsson, Hossein Azizpour, Mårten Björkman

Figure 1 for Hyperplane Arrangements of Trained ConvNets Are Biased
Figure 2 for Hyperplane Arrangements of Trained ConvNets Are Biased
Figure 3 for Hyperplane Arrangements of Trained ConvNets Are Biased
Figure 4 for Hyperplane Arrangements of Trained ConvNets Are Biased

  Access Paper or Ask Questions

On the use of recurrent neural networks for predictions of turbulent flows


Feb 04, 2020
Luca Guastoni, Prem A. Srinivasan, Hossein Azizpour, Philipp Schlatter, Ricardo Vinuesa

Figure 1 for On the use of recurrent neural networks for predictions of turbulent flows
Figure 2 for On the use of recurrent neural networks for predictions of turbulent flows
Figure 3 for On the use of recurrent neural networks for predictions of turbulent flows
Figure 4 for On the use of recurrent neural networks for predictions of turbulent flows

  Access Paper or Ask Questions

Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation


Jun 12, 2019
Erik Englesson, Hossein Azizpour

Figure 1 for Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation
Figure 2 for Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation
Figure 3 for Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation
Figure 4 for Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation
* Submitted at the ICML 2019 Workshop on Uncertainty & Robustness in Deep Learning(poster & spotlight talk) 
  Access Paper or Ask Questions

Explainability Techniques for Graph Convolutional Networks


May 31, 2019
Federico Baldassarre, Hossein Azizpour

Figure 1 for Explainability Techniques for Graph Convolutional Networks
Figure 2 for Explainability Techniques for Graph Convolutional Networks
Figure 3 for Explainability Techniques for Graph Convolutional Networks
Figure 4 for Explainability Techniques for Graph Convolutional Networks
* Accepted at the ICML 2019 Workshop "Learning and Reasoning with Graph-Structured Representations" (poster + spotlight talk) 
  Access Paper or Ask Questions

The role of artificial intelligence in achieving the Sustainable Development Goals


Apr 30, 2019
Ricardo Vinuesa, Hossein Azizpour, Iolanda Leite, Madeline Balaam, Virginia Dignum, Sami Domisch, Anna Felländer, Simone Langhans, Max Tegmark, Francesco Fuso Nerini

Figure 1 for The role of artificial intelligence in achieving the Sustainable Development Goals
Figure 2 for The role of artificial intelligence in achieving the Sustainable Development Goals
Figure 3 for The role of artificial intelligence in achieving the Sustainable Development Goals
Figure 4 for The role of artificial intelligence in achieving the Sustainable Development Goals

  Access Paper or Ask Questions

GANtruth - an unpaired image-to-image translation method for driving scenarios


Nov 26, 2018
Sebastian Bujwid, Miquel Martí, Hossein Azizpour, Alessandro Pieropan

Figure 1 for GANtruth - an unpaired image-to-image translation method for driving scenarios
Figure 2 for GANtruth - an unpaired image-to-image translation method for driving scenarios
Figure 3 for GANtruth - an unpaired image-to-image translation method for driving scenarios
Figure 4 for GANtruth - an unpaired image-to-image translation method for driving scenarios
* 32nd Conference on Neural Information Processing Systems (NeurIPS), Machine Learning for Intelligent Transportation Systems Workshop, Montr\'eal, Canada. 2018 
  Access Paper or Ask Questions

Bayesian Uncertainty Estimation for Batch Normalized Deep Networks


Jul 16, 2018
Mattias Teye, Hossein Azizpour, Kevin Smith

Figure 1 for Bayesian Uncertainty Estimation for Batch Normalized Deep Networks
Figure 2 for Bayesian Uncertainty Estimation for Batch Normalized Deep Networks
Figure 3 for Bayesian Uncertainty Estimation for Batch Normalized Deep Networks
Figure 4 for Bayesian Uncertainty Estimation for Batch Normalized Deep Networks
* ICML 2018 
  Access Paper or Ask Questions

Factors of Transferability for a Generic ConvNet Representation


Jul 15, 2015
Hossein Azizpour, Ali Sharif Razavian, Josephine Sullivan, Atsuto Maki, Stefan Carlsson

Figure 1 for Factors of Transferability for a Generic ConvNet Representation
Figure 2 for Factors of Transferability for a Generic ConvNet Representation
Figure 3 for Factors of Transferability for a Generic ConvNet Representation
Figure 4 for Factors of Transferability for a Generic ConvNet Representation
* Extended version of the workshop paper with more experiments and updated text and title. Original CVPR15 DeepVision workshop paper title: "From Generic to Specific Deep Representations for Visual Recognition" 
  Access Paper or Ask Questions

Spotlight the Negatives: A Generalized Discriminative Latent Model


Jul 08, 2015
Hossein Azizpour, Mostafa Arefiyan, Sobhan Naderi Parizi, Stefan Carlsson

Figure 1 for Spotlight the Negatives: A Generalized Discriminative Latent Model
Figure 2 for Spotlight the Negatives: A Generalized Discriminative Latent Model
Figure 3 for Spotlight the Negatives: A Generalized Discriminative Latent Model
Figure 4 for Spotlight the Negatives: A Generalized Discriminative Latent Model
* Published in proceedings of BMVC 2015 
  Access Paper or Ask Questions

Persistent Evidence of Local Image Properties in Generic ConvNets


Nov 24, 2014
Ali Sharif Razavian, Hossein Azizpour, Atsuto Maki, Josephine Sullivan, Carl Henrik Ek, Stefan Carlsson

Figure 1 for Persistent Evidence of Local Image Properties in Generic ConvNets

  Access Paper or Ask Questions

Self-tuned Visual Subclass Learning with Shared Samples An Incremental Approach


May 26, 2014
Hossein Azizpour, Stefan Carlsson

Figure 1 for Self-tuned Visual Subclass Learning with Shared Samples An Incremental Approach
Figure 2 for Self-tuned Visual Subclass Learning with Shared Samples An Incremental Approach
Figure 3 for Self-tuned Visual Subclass Learning with Shared Samples An Incremental Approach
Figure 4 for Self-tuned Visual Subclass Learning with Shared Samples An Incremental Approach
* Updated ICCV 2013 submission 
  Access Paper or Ask Questions

CNN Features off-the-shelf: an Astounding Baseline for Recognition


May 12, 2014
Ali Sharif Razavian, Hossein Azizpour, Josephine Sullivan, Stefan Carlsson

Figure 1 for CNN Features off-the-shelf: an Astounding Baseline for Recognition
Figure 2 for CNN Features off-the-shelf: an Astounding Baseline for Recognition
Figure 3 for CNN Features off-the-shelf: an Astounding Baseline for Recognition
Figure 4 for CNN Features off-the-shelf: an Astounding Baseline for Recognition
* version 3 revisions: 1)Added results using feature processing and data augmentation 2)Referring to most recent efforts of using CNN for different visual recognition tasks 3) updated text/caption 
  Access Paper or Ask Questions