GANEx: A complete pipeline of training, inference and benchmarking GAN experiments
MetadataShow full item record
Original versionThambawita, Hammer, Riegler, Halvorsen: GANEx: A complete pipeline of training, inference and benchmarking GAN experiments. In: Gurrin CG, Jónsson BT, Peteri R. Proceedings of Content Based Multimedia Information (CBMI 2019), 2019. IEEE conference proceedings https://dx.doi.org/10.1109/CBMI.2019.8877387
Deep learning (DL) is one of the standard methods in the field of multimedia research to perform data classification, detection, segmentation and generation. Within DL, generative adversarial networks (GANs) represents a new and highly popular branch of methods. GANs have the capability to generate, from random noise or conditional input, new data realizations within the dataset population. While generation is popular and highly useful in itself, GANs can also be useful to improve supervised DL. GAN-based approaches can, for example, perform segmentation or create synthetic data for training other DL models. The latter one is especially interesting in domains where not much training data exists such as medical multimedia. In this respect, performing a series of experiments involving GANs can be very time consuming due to the lack of tools that support the whole pipeline such as structured training, testing and tracking of different architectures and configurations. Moreover, the success of generative models is highly dependent on hyper-parameter optimization and statistical analysis in the design and fine-tuning stages. In this paper, we present a new tool called GANEx for making the whole pipeline of training, inference and benchmarking GANs faster, more efficient and more structured. The tool consists of a special library called FastGAN which allows designing generative models very fast. Moreover, GANEx has a graphical user interface to support structured experimenting, quick hyper-parameter configurations and output analysis. The presented tool is not limited to a specific DL framework and can be therefore even used to compare the performance of cross frameworks.
SeriesInternational Workshop on Content-Based Multimedia Indexing, CBMI;
Showing items related by title, author, creator and subject.
Dzogovic, Bruno; Do, Van Thuan; Feng, Boning; Do, van Thanh (2018 IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE);, Chapter; Peer reviewed, 2018-07-09)The upcoming 5G mobile networks will not only bring high data rates but also deliver flexibility and adaptability, which is conveyed by the virtualization of the mobile network. Unfortunately, virtualization of mobile ...
Dzogovic, Bruno; Santos, Bernardo; Do, Thuan Van; Feng, Boning; Jacot, Niels; Do, van Thanh (IEEE International Conference on Cyber Security and Cloud Computing (CSCloud);2019 6th IEEE International Conference on Cyber Security and Cloud Computing (CSCloud)/ 2019 5th IEEE International Conference on Edge Computing and Scalable Cloud (EdgeCom), Conference object, 2019-10-03)Cloud-Radio Access Networks are one of the main enablers for driving the 5G technology. They allow creation and utilization of core network components in a precise flexible manner that implies of the possibility for resource ...
Within-network connectivity in the salience network after attention bias modification training in residual depression: Report from a preregistered clinical trial Hilland, Eva; Landrø, Nils Inge; Harmer, Catherine; Maglanoc, Luigi Angelo; Jonassen, Rune (Frontiers in Human Neuroscience; December 2018, Volume 12, Article 508, Journal article; Peer reviewed, 2018-12-21)Alterations in resting state networks (RSNs) are associated with emotional- and attentional control difficulties in depressed individuals. Attentional bias modification (ABM) training may lead to more adaptive emotional ...