Fabian Mentzer

Learn More
We propose a highly structured neural network architecture for semantic segmentation with an extremely small model size, suitable for low-power embedded and mobile platforms. Specifically, our architecture combines i) a Haar waveletbased tree-like convolutional neural network (CNN), ii) a random layer realizing a radial basis function kernel approximation,(More)
In this work we present a new approach to learn compressible representations in deep architectures with an end-to-end training strategy. Our method is based on a soft (continuous) relaxation of quantization and entropy, which we anneal to their discrete counterparts throughout training. We showcase this method for two challenging applications: Image(More)
While most common literature search engines use search queries based on keywords, we are interested in finding important as well as relevant literature based on other literature. To accomplish this, we introduce the PaperRank algorithm, an adapted version of the PageRank algorithm. PaperRank attributes a single score of absolute importance to scientific(More)
  • 1