AbstractBinary neural networks are a promising approach to execute convolutional neural networks on devices with low computational power. Previous work on this subject often quantizes pretrained full-precision models and uses complex training strategies. In our work, we focus on increasing the performance of binary neural networks by training from scratch with a simple training strategy. In our experiments we show that we are able to achieve state-of-the-art results on standard benchmark datasets. Further, we analyze how full-precision network structures can be adapted for efficient binary networks and adopt a network architecture based on a DenseNet for binary networks, which lets us improve the state-of-the-art even further. Our source code can be found online: https://github.com/hpi-xnor/BMXNet-v2
LoANs: Weakly Supervised Object Detection with Localizer Assessor Networks.Bartz, Christian; Yang, Haojin; Bethge, Joseph; Meinel, Christoph (2018). 341--356.
Improving Layout Quality by Mixing Treemap-Layouts Based on Data-Change Characteristics.Bethge, Joseph; Hahn, Sebastian; Döllner, Jürgen M. Hullin, Klein, R., Schultz, T., Yao, A. (reds.) (2017). (Vol. 2017)
AbstractThis paper presents a hybrid treemap layout approach that optimizes layout-quality metrics by combining state-of-the-art treemap layout algorithms. It utilizes machine learning to predict those metrics based on data metrics describing the characteristics and changes of the dataset. For this, the proposed approach uses a neural network which is trained on artificially generated dataset,s containing a total of 15.8 million samples. The resulting model is integrated into an approach called Smart-Layouting. This approach is evaluated on real-world data from 100 publicly available software repositories. Compared to other state-of-the-art treemap algorithms it reaches an overall better result. Additionally, this approach can be customized by an end user’s needs. The customization allows for specifying weights for the importance of each layout-quality metric. The results indicate, that the algorithm is able to adapt successfully towards a given set of weights.
Relative Direction Change: A Topology-based Metric for Layout Stability in Treemaps.Hahn, Sebastian; Bethge, Joseph; Döllner, Jürgen (2017).