Ali Dabouei


Email: ad0046 [at] mix [dot] wvu [dot] edu

Lane Department of Computer Science & Electrical Engineering
West Virginia University
Morgantown, WV, USA

I am a PhD candidate in the Department of Computer Science and Electrical Engineering at West Virginia University, working with Prof. Nasrabadi. I am interested in deep learning, machine learning (ML), mathematics, pattern recognition, and computer vision. Currently, I am studying adversarial ML, network compression, interpretable ML, and unsupervised representation learning. I am also working on applications of deep learning in computer vision and biometrics.

I am passionate about any ML topic, but currently, these are the specials:

  • Adversarial ML
  • Network Compression
  • Interpretable ML
  • Unsupervised Learning

Community Services: Reviewer for ICCV2021, CVPR2021 (Outstanding Reviewer), TPAMI, TNNLS, BMVC, etc.


Recent Publications

Responsive image
SuperMix: Supervising the Mixing Data Augmentation

Ali Dabouei, Sobhan Soleymani, Fariborz Taherkhani, Nasser M. Nasrabadi
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

[PDF] [Code]

Self-Supervised Wasserstein Pseudo-Labeling for Semi-Supervised Image Classification

Fariborz Taherkhani, Ali Dabouei, Sobhan Soleymani, Jeremy Dawson, Nasser M. Nasrabadi
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

[PDF]

Responsive image
Mutual Information Maximization on Disentangled Representations for Differential Morph Detection

Sobhan Soleymani, Ali Dabouei, Fariborz Taherkhani, Jeremy Dawson, Nasser M. Nasrabadi
IEEE Winter Conference on Applications of Computer Vision (WACV), 2021.

[PDF]

Responsive image
Transporting Labels via Hierarchical Optimal Transport for Semi-Supervised Learning

Fariborz Taherkhani, Ali Dabouei, Sobhan Soleymani, Jeremy Dawson, Nasser M. Nasrabadi
European Conference on Computer Vision (ECCV), 2020.

[PDF]

Responsive image
Attribute Adaptive Margin Softmax Loss using Privileged Information

Mehdi Iranmanesh, Ali Dabouei, Nasser M. Nasrabadi
British Machine Vision Conference (BMVC), 2020.

[PDF]

Responsive image
Exploiting Joint Robustness to Adversarial Perturbations

Ali Dabouei, Sobhan Soleymani, Fariborz Taherkhani, Jeremy Dawson, Nasser M. Nasrabadi
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

[PDF]

Responsive image
SmoothFool: An Efficient Framework for Computing Smooth Adversarial Perturbations

Ali Dabouei, Sobhan Soleymani, Fariborz Taherkhani, Jeremy Dawson, Nasser M. Nasrabadi
IEEE Winter Conference on Applications of Computer Vision (WACV), 2020.

[PDF] [Code]

Responsive image
Boosting Deep Face Recognition via Disentangling Appearance and Geometry

Ali Dabouei, Fariborz Taherkhani, Sobhan Soleymani, Jeremy Dawson, Nasser M. Nasrabadi
IEEE Winter Conference on Applications of Computer Vision (WACV), 2020.

[PDF]

Responsive image
Robust Facial Landmark Detection via Aggregation on Geometrically Manipulated Faces

Seyed Mehdi Iranmanesh, Ali Dabouei, Sobhan Soleymani, Hadi Kazemi, Nasser Nasrabadi
IEEE Winter Conference on Applications of Computer Vision (WACV), 2020.

[PDF]

Responsive image
A Weakly Supervised Fine Label Classifier Enhanced by Coarse Supervision

Fariborz Taherkhani, Hadi Kazemi, Ali Dabouei, Jeremy Dawson, Nasser M. Nasrabadi
International Conference on Computer Vision (ICCV), 2019.

[PDF]

Responsive image
Fast Geometrically-Perturbed Adversarial Faces

Ali Dabouei, Sobhan Soleymani, Jeremy Dawson, Nasser M. Nasrabadi
IEEE Winter Conference on Applications of Computer Vision (WACV), 2019.

[PDF] [Code]

Patent

Responsive image
Fingerprint Distortion Rectification using Deep Convolutional Neural Networks

Nasser M. Nasrabadi, Jeremy Dawson, Ali Dabouei
US Patent App. 16/791,757.

[PDF]

Plain Academic