Mohamed Azzam

About Mohamed Azzam

Mohamed Azzam, With an exceptional h-index of 4 and a recent h-index of 4 (since 2020), a distinguished researcher at City University of Hong Kong, specializes in the field of Machine Learning, Computer Vision.

His recent articles reflect a diverse array of research interests and contributions to the field:

Adversarially Smoothed Feature Alignment for Visual Domain Adaptation

Unsupervised domain adaptation VIA cluster alignment with maximum classifier discrepancy

Knowledge exchange between domain-adversarial and private networks improves open set image classification

Behavior regularized prototypical networks for semi-supervised few-shot image classification

Adversarially Constrained Interpolation for Unsupervised Domain Adaptation

KTransGAN: Variational inference-based knowledge transfer for unsupervised conditional generative learning

Mohamed Azzam Information

University

Position

PhD student

Citations(all)

46

Citations(since 2020)

46

Cited By

2

hIndex(all)

4

hIndex(since 2020)

4

i10Index(all)

2

i10Index(since 2020)

2

Email

University Profile Page

Google Scholar

Mohamed Azzam Skills & Research Interests

Machine Learning

Computer Vision

Top articles of Mohamed Azzam

Adversarially Smoothed Feature Alignment for Visual Domain Adaptation

2021/7/18

Unsupervised domain adaptation VIA cluster alignment with maximum classifier discrepancy

2021/7/5

Knowledge exchange between domain-adversarial and private networks improves open set image classification

IEEE Transactions on Image Processing

2021/6/17

Behavior regularized prototypical networks for semi-supervised few-shot image classification

Pattern Recognition

2021/4

Adversarially Constrained Interpolation for Unsupervised Domain Adaptation

2021/1/10

KTransGAN: Variational inference-based knowledge transfer for unsupervised conditional generative learning

IEEE Transactions on Multimedia

2020/9/14

See List of Professors in Mohamed Azzam University(City University of Hong Kong)

Co-Authors

academic-engine