M
Muhammad Ferjad Naeem
Researcher at University of Tübingen
Publications - 20
Citations - 391
Muhammad Ferjad Naeem is an academic researcher from University of Tübingen. The author has contributed to research in topics: Computer science & Cosine similarity. The author has an hindex of 7, co-authored 16 publications receiving 130 citations. Previous affiliations of Muhammad Ferjad Naeem include University of the Sciences & Technische Universität München.
Papers
More filters
Posted Content
Reliable Fidelity and Diversity Metrics for Generative Models
TL;DR: It is shown that even the latest version of the precision and recall metrics are not reliable yet, and density and coverage metrics provide more interpretable and reliable signals for practitioners than the existing metrics.
Proceedings ArticleDOI
Learning Graph Embeddings for Compositional Zero-shot Learning
TL;DR: In this paper, the authors propose a novel graph formulation called Compositional Graph Embedding (CGE) that learns image features, compositional classifiers and latent representations of visual primitives in an end-to-end manner.
Proceedings ArticleDOI
Open World Compositional Zero-Shot Learning
TL;DR: In this article, the authors proposed to use the cosine similarity between visual features and compositional embeddings to mask the output space and boost the performance of the CZSL model in the open world scenario.
Proceedings Article
Reliable Fidelity and Diversity Metrics for Generative Models
TL;DR: In this paper, the authors proposed density and coverage metrics for image generation, which provide more interpretable and reliable signals for practitioners than the existing metrics, such as precision and recall.
Posted Content
Data Augmentation with Manifold Exploring Geometric Transformations for Increased Performance and Robustness
Magdalini Paschali,Walter Simson,Abhijit Guha Roy,Muhammad Ferjad Naeem,Rüdiger Göbl,Christian Wachinger,Nassir Navab +6 more
TL;DR: A novel augmentation technique that improves not only the performance of deep neural networks on clean test data, but also significantly increases their robustness to random transformations, both affine and projective.