Search Results for author: Roland Vollgraf

Found 17 papers, 10 papers with code

Grid Partitioned Attention: Efficient TransformerApproximation with Inductive Bias for High Resolution Detail Generation

1 code implementation8 Jul 2021 Nikolay Jetchev, Gökhan Yildirim, Christian Bracher, Roland Vollgraf

Attention is a general reasoning mechanism than can flexibly deal with image information, but its memory requirements had made it so far impractical for high resolution image generation.

Conditional Image Generation Deep Attention +1

Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting

1 code implementation28 Jan 2021 Kashif Rasul, Calvin Seward, Ingmar Schuster, Roland Vollgraf

In this work, we propose \texttt{TimeGrad}, an autoregressive model for multivariate probabilistic time series forecasting which samples from the data distribution at each time step by estimating its gradient.

Multivariate Time Series Forecasting Probabilistic Time Series Forecasting +1

Task-Aware Representation of Sentences for Generic Text Classification

1 code implementation COLING 2020 Kishaloy Halder, Alan Akbik, Josip Krapac, Roland Vollgraf

State-of-the-art approaches for text classification leverage a transformer architecture with a linear layer on top that outputs a class distribution for a given prediction problem.

Binary Classification text-classification +2

CRISP: A Probabilistic Model for Individual-Level COVID-19 Infection Risk Estimation Based on Contact Data

1 code implementation9 Jun 2020 Ralf Herbrich, Rajeev Rastogi, Roland Vollgraf

We present CRISP (COVID-19 Risk Score Prediction), a probabilistic graphical model for COVID-19 infection spread through a population based on the SEIR model where we assume access to (1) mutual contacts between pairs of individuals across time across various channels (e. g., Bluetooth contact traces), as well as (2) test outcomes at given times for infection, exposure and immunity tests.

Time Series Analysis

Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows

1 code implementation ICLR 2021 Kashif Rasul, Abdul-Saboor Sheikh, Ingmar Schuster, Urs Bergmann, Roland Vollgraf

In this work we model the multivariate temporal dynamics of time series via an autoregressive deep learning model, where the data distribution is represented by a conditioned normalizing flow.

Decision Making Multivariate Time Series Forecasting +3

Set Flow: A Permutation Invariant Normalizing Flow

no code implementations6 Sep 2019 Kashif Rasul, Ingmar Schuster, Roland Vollgraf, Urs Bergmann

We present a generative model that is defined on finite sets of exchangeable, potentially high dimensional, data.

A Deep Learning System for Predicting Size and Fit in Fashion E-Commerce

3 code implementations23 Jul 2019 Abdul-Saboor Sheikh, Romain Guigoures, Evgenii Koriagin, Yuen King Ho, Reza Shirvany, Roland Vollgraf, Urs Bergmann

To alleviate this problem, we propose a deep learning based content-collaborative methodology for personalized size and fit recommendation.

Collaborative Filtering Entity Embeddings

Learning Set-equivariant Functions with SWARM Mappings

1 code implementation22 Jun 2019 Roland Vollgraf

The architecture is based on a gated recurrent network which is iteratively applied to all entities individually and at the same time syncs with the progression of the whole population.

A Bandit Framework for Optimal Selection of Reinforcement Learning Agents

no code implementations10 Feb 2019 Andreas Merentitis, Kashif Rasul, Roland Vollgraf, Abdul-Saboor Sheikh, Urs Bergmann

This helps the bandit framework to select the best agents early, since these rewards are smoother and less sparse than the environment reward.

Inductive Bias reinforcement-learning +1

Studio2Shop: from studio photo shoots to fashion articles

no code implementations2 Jul 2018 Julia Lasserre, Katharina Rasch, Roland Vollgraf

Fashion is an increasingly important topic in computer vision, in particular the so-called street-to-shop task of matching street images with shop images containing similar fashion items.

Retrieval Test

Syntax-Aware Language Modeling with Recurrent Neural Networks

no code implementations2 Mar 2018 Duncan Blythe, Alan Akbik, Roland Vollgraf

Neural language models (LMs) are typically trained using only lexical features, such as surface forms of words.

Language Modelling

Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms

37 code implementations25 Aug 2017 Han Xiao, Kashif Rasul, Roland Vollgraf

We present Fashion-MNIST, a new dataset comprising of 28x28 grayscale images of 70, 000 fashion products from 10 categories, with 7, 000 images per category.

Benchmarking BIG-bench Machine Learning +1

An LSTM-Based Dynamic Customer Model for Fashion Recommendation

no code implementations24 Aug 2017 Sebastian Heinz, Christian Bracher, Roland Vollgraf

Online fashion sales present a challenging use case for personalized recommendation: Stores offer a huge variety of items in multiple sizes.

Collaborative Filtering

Learning Texture Manifolds with the Periodic Spatial GAN

7 code implementations ICML 2017 Urs Bergmann, Nikolay Jetchev, Roland Vollgraf

Second, we show that the image generation with PSGANs has properties of a texture manifold: we can smoothly interpolate between samples in the structured noise space and generate novel samples, which lie perceptually between the textures of the original dataset.

Image Generation Texture Synthesis

Texture Synthesis with Spatial Generative Adversarial Networks

3 code implementations24 Nov 2016 Nikolay Jetchev, Urs Bergmann, Roland Vollgraf

Generative adversarial networks (GANs) are a recent approach to train generative models of data, which have been shown to work particularly well on image data.

Texture Synthesis

Fashion DNA: Merging Content and Sales Data for Recommendation and Article Mapping

no code implementations8 Sep 2016 Christian Bracher, Sebastian Heinz, Roland Vollgraf

Interpretation of the metric of these spaces is straightforward: The product of Fashion DNA and customer style vectors yields the forecast purchase likelihood for the customer-item pair, while the angle between Fashion DNA vectors is a measure of item similarity.


Cannot find the paper you are looking for? You can Submit a new open access paper.