176 citations · 250 across the 54 of their papers we have counts for
7 papers · 1 filter
Spectral Distribution Aware Image Generation
Steffen Jung, Margret Keuper
Recent advances in deep generative models for photo-realistic images have led to high quality visual results. Such models learn to generate data from a given training distribution…
Neural Architecture Performance Prediction Using Graph Neural Networks
Jovita Lukasik, David Friede, Heiner Stuckenschmidt +1
In computer vision research, the process of automating architecture engineering, Neural Architecture Search (NAS), has gained substantial interest. Due to the high computational co…
Smooth Variational Graph Embeddings for Efficient Neural Architecture Search
Jovita Lukasik, David Friede, Arber Zela +2
Neural architecture search (NAS) has recently been addressed from various directions, including discrete, sampling-based methods and efficient differentiable approaches. While the…
Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarks
Arber Zela, Julien Siems, Lucas Zimmer +3
The most significant barrier to the advancement of Neural Architecture Search (NAS) is its demand for large computational resources, which hinders scientifically sound empirical ev…
Learning Embeddings for Image Clustering: An Empirical Study of Triplet Loss Approaches
Kalun Ho, Janis Keuper, Franz-Josef Pfreundt +1
In this work, we evaluate two different image clustering objectives, k-means clustering and correlation clustering, in the context of Triplet Loss induced feature space embeddings.…
Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions
Ricard Durall, Margret Keuper, Janis Keuper
Generative convolutional deep neural networks, e.g. popular GAN architectures, are relying on convolution based up-sampling methods to produce non-scalar outputs like images or vid…
Unsupervised Multiple Person Tracking using AutoEncoder-Based Lifted Multicuts
Kalun Ho, Janis Keuper, Margret Keuper
Multiple Object Tracking (MOT) is a long-standing task in computer vision. Current approaches based on the tracking by detection paradigm either require some sort of domain knowled…