Selected Publications

For a full list, have a look at my Google Scholar page.

Improved Techniques for Training Single-Image GANs

Improving the results and training speed of single-image GANs.

T. Hinz, M. Fisher, O. Wang, S. Wermter, Under Review 2020.

Semantic Object Accuracy for Generative Text-to-Image Synthesis

A novel GAN architecture and an improved metric to evaluate generative text-to-image synthesis models.

T. Hinz, S. Heinrich, S. Wermter, IEEE Transactions on Pattern Analysis and Machine Intelligence 2020.

Generating Multiple Objects at Spatially Distinct Locations

Fine-grained control over the placement and identity of objects in images generated with a Generative Adversarial Network.

T. Hinz, S. Heinrich, S. Wermter, International Conference on Learning Representations 2019.

Image Generation and Translation with Disentangled Representations

Controllable image generation and translation with very little supervision.

T. Hinz, S. Wermter, IEEE International Joint Conference on Neural Networks 2018.

Speeding Up the Hyperparameter Optimization Of Deep Convolutional Neural Networks

How to use lower dimensional data representations to speed up the hyperparameter optimization for CNNs processing images..

T. Hinz, N. Navarro-Guerrero, S. Magg, S. Wermter, International Journal of Computational Intelligence and Applications 2018.

Inferencing Based on Unsupervised Learning of Disentangled Representations

Unsupervised learning of disentangled representations with a Bidirectional GAN.

T. Hinz, S. Wermter, European Symposium on Artificial Neural Networks 2018.

The Effects of Regularization on Learning Facial Expressions with Convolutional Neural Networks

How modern regularization techniques for CNNs affect the learned representations.

T. Hinz, P. Barros, S. Wermter, International Conference on Artificial Neural Networks 2016.

Back to Home