Sadaf Gulshad

I am a PhD student in Machine Learning and Computer Vision at Bosch Delta Lab, University of Amsterdam under the supervision of Prof. Dr. Arnold Smeulders.

Before starting my PhD I completed my masters in Electrical Engineering from KAIST, South Korea under the supervision of Prof. Dr. Jong-Hwan Kim in Robotics Intelligence Technology lab. I completed my bachelors in Electrical and Computer Engineering from COMSATS Institute of Information and Technology, Pakistan.

Current Research Interests:

Machine Learning and Computer Vision. More concretely Robustness of Neural Networks, Robustification through Adversarial and Natural Perturbations, Explainable AI, Explainability using Visual Attributes, Studying Counterintuitive Visual Attributes and Adversarial Examples.

My detailed cv can be found here.

Research Publications and Preprints:

Sadaf Gulshad, Ivan Sosnovik and Arnold Smeulders. Wiggling Weights to Improve the Robustness of Classifiers. arXiv e-prints (2021) Paper.
Sadaf Gulshad, Ivan Sosnovik and Arnold Smeulders. Built-in Elastic Transformations for Improved Robustness. arXiv e-prints (2021) Paper.
Sadaf Gulshad and Arnold Smeulders. Natural Perturbed Training for General Robustness of Neural Network Classifiers. arXiv e-prints (2021) Paper.
Sadaf Gulshad and Arnold Smeulders. Counterfactual Attribute-based Visual Explanations for Classification. International Journal of Multimedia Information Retrieval (IJMIR2021).
Sadaf Gulshad and Arnold Smeulders. Explaining with Counter Visual Attributes and Examples. International Conference on Multimedia Retrieval (ICMR 2020), ACM. Paper, Code. Selected in Best paper session for an oral presentation. Presentation video.
Sadaf Gulshad, Jan Hendrik Metzen, and Arnold Smeulders. "Adversarial and Natural Perturbations for General Robustness." arXiv e-prints (2020) Paper
Sadaf Gulshad, Jan Hendrik Metzen, Arnold Smeulders, and Zeynep Akata. "Interpreting adversarial examples with attributes." arXiv preprint (2019). Paper
Sadaf Gulshad, Dick Sigmund, and Jong-Hwan Kim. "Learning to reproduce stochastic time series using stochastic LSTM." In 2017 International Joint Conference on Neural Networks (IJCNN), pp. 859-866. IEEE, 2017. Paper
Sadaf Gulshad, and Jong-Hwan Kim. "Deep convolutional and recurrent writer." In 2017 International Joint Conference on Neural Networks (IJCNN), pp. 2836-2842. IEEE, 2017. Paper

Teaching and Graduate Student Supervision:

  • I was teaching assistant for "Applied Machine Learning" in 2017, and "Machine Learning" in 2018 and 2019.
  • Supervised Arend van Dormalen for his masters thesis entitled "Image-Level Supervised Semantic Segmentation with Network Attention and Saliency Priors."
  • Supervised Jeroen Vranken for his masters thesis entitled "Systematic Comparison of Uncertainty Estimation Methods for Diagnosing Heart Disease in Electrocardiograms using Deep Learning."
  • Supervised Mehdi Güneş for his masters thesis entitled "Exploring the effect of data imperfections in clinical data on model performance."
  • Supervised Bella Nicholson for her masters thesis entitled "Interpretable Representation Learning for Relational Data."
  • Contact Details

    s[dot]gulshad[at]uva[dot]nl

    University of Amsterdam Science Park 904, Room C3.201 1098XH Amsterdam The Netherlands