Skip to search formSkip to main contentSkip to account menu
  • Publications
  • Influence
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
TLDR
This work proposes a two time-scale update rule (TTUR) for training GANs with stochastic gradient descent on arbitrary GAN loss functions and introduces the "Frechet Inception Distance" (FID) which captures the similarity of generated images to real ones better than the Inception Score.
View PDF on arXiv
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
TLDR
Vision Transformer (ViT) attains excellent results compared to state-of-the-art convolutional networks while requiring substantially fewer computational resources to train.
View PDF on arXiv
Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
TLDR
The "exponential linear unit" (ELU) which speeds up learning in deep neural networks and leads to higher classification accuracies and significantly better generalization performance than ReLUs and LReLUs on networks with more than 5 layers.
View PDF on arXiv
Self-Normalizing Neural Networks
TLDR
Self-normalizing neural networks (SNNs) are introduced to enable high-level abstract representations and it is proved that activations close to zero mean and unit variance that are propagated through many network layers will converge towards zero meanand unit variance -- even under the presence of noise and perturbations.
View PDF on arXiv
MLP-Mixer: An all-MLP Architecture for Vision
TLDR
It is shown that while convolutions and attention are both sufficient for good performance, neither of them are necessary, and MLP-Mixer, an architecture based exclusively on multi-layer perceptrons (MLPs), attains competitive scores on image classification benchmarks.
View PDF on arXiv
Object-Centric Learning with Slot Attention
TLDR
An architectural component that interfaces with perceptual representations such as the output of a convolutional neural network and produces a set of task-dependent abstract representations which are exchangeable and can bind to any object in the input by specializing through a competitive procedure over multiple rounds of attention is presented.
View PDF on arXiv
GANs Trained by a Two Time-Scale Update Rule Converge to a Nash Equilibrium
Towards Accurate Generative Models of Video: A New Metric & Challenges
TLDR
A large-scale human study is contributed, which confirms that FVD correlates well with qualitative human judgment of generated videos, and provides initial benchmark results on SCV.
View PDF on arXiv
DeepTox: Toxicity Prediction using Deep Learning
TLDR
DeepTox had the highest performance of all computational methods winning the grand challenge, the nuclear receptor panel, the stress response panel, and six single assays (teams ``Bioinf@JKU'').
View via Publisher
Do Vision Transformers See Like Convolutional Neural Networks?
TLDR
Analyzing the internal representation structure of ViTs and CNNs on image classification benchmarks, there are striking differences between the two architectures, such as ViT having more uniform representations across all layers and ViT residual connections, which strongly propagate features from lower to higher layers.
View PDF on arXiv
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License