Azade Farshad


Picture of Azade Farshad

M.Sc. Azade Farshad

Technical University of Munich

Institute of Informatics

Place of employment

Informatics 16 - Chair of Computer Aided Medical Procedures (Prof. Navab)

Work:
Boltzmannstr. 3(5613)/III
85748 Garching b. München

Research interests

  • Unsupervised Learning
  • Self-Supervised Learning
  • Meta-learning
  • Scene graphs
  • Generative Models
  • Optimization

Research Projects

  • MIGS: Meta Image Generation from Scene Graphs (BMVC 2021) Project Page
  • Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information (NeurIPS 2021) Code
  • Unconditional Scene Graph Generation (ICCV 2021) Project Page
  • Inverse Distance Aggregation for Federated Learning (MICCAI Workshop 2020) Project Page
  • Semantic Image Manipulation using Scene Graphs (CVPR 2020) Project Page | Code
  • Neural Network Compression (ECCV Workshop 2018) Project Page

Student Projects

Feel free to contact me for any of the following projects, or if you are interested in related topics.

Type Title Student Status
Master Thesis

Semantic Image Manipulation using Objectwise Graph Feature

Extraction

Pavel Jahoda Running
Master Thesis Towards Medical Image Segmentation using Self-Supervised Learning Peter Weinberger Running
Master Thesis Human Role Prediction Using Knowledge Graphs Aleksandr Zuev Running
Guided Research

Meta-learning for Computer Vision using Evolutionary Algorithms

Sraddha Das Finished
Master Thesis Self-supervised learning using Contrastive Generative Models Anastasia Makarevich Running
Master Thesis Scene graph generation Sarthak Garg Finished
Master Thesis Meta-learning for Image Generation/Manipulation using Scene Graphs Sabrina Musatian Finished
Guided Research Meta-learning for Medical Image Segmentation Anastasia Makarevich Finished
Master Thesis Meta-clustering Samin Hamidi Finished
Master Thesis Towards More Robust Machine Learning Models Mariem Kthiri Finished
Master Thesis Federated Learning with Non-iid data Yousef Yegane Finished
Guided Research Robustness of Knowledge Transfer Methods Yousef Yegane Finished

Professional Services

  • Reviewer at:
    • CVPR, ICCV, ICLR, ECCV, BMVC, WACV, ACCV

Publications

  • Garg, Sarthak; Dhamo, Helisa; Farshad, Azade; Musatian, Sabrina; Navab, Nassir; Tombari, Federico: Unconditional Scene Graph Generation. IEEE International Conference on Computer Vision (ICCV), 2021 more…
  • Zhang, Yang; Khakzar, Ashkan; Li, Yawei; Farshad, Azade; Kim, Seong Tae; Navab, Nassir: Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information. Thirty-Fifth Conference on Neural Information Processing Systems, 2021 more…
  • Yeganeh, Yousef; Farshad, Azade; Navab, Nassir; Albarqouni, Shadi: Inverse Distance Aggregation for Federated Learning with Non-IID Data. In: Domain Adaptation and Representation Transfer, and Distributed and Collaborative Learning. Springer International Publishing, 2020 more…
  • Dhamo, Helisa; Farshad, Azade; Laina, Iro; Navab, Nassir; Hager, Gregory D.; Tombari, Federico; Rupprecht, Christian: Semantic Image Manipulation Using Scene Graphs. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2020 more…
  • Belagiannis, Vasileios; Farshad, Azade; Galasso, Fabio: Adversarial Network Compression. In: Lecture Notes in Computer Science. Springer International Publishing, 2019 more…