Search Results for author:
Found 10 papers, 0 papers with code
Instant Complexity Reduction in CNNs using Locality-Sensitive Hashing
In particular, we are able to instantly drop 46. 72% of FLOPs while only losing 1. 25% accuracy by just swapping the convolution modules in a ResNet34 on CIFAR-10 for our HASTE module.
Deep Neural Networks with Efficient Guaranteed Invariances
We then address the problem of incorporating multiple desired invariances into a single network.
Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Survey
By freezing weights, the number of trainable parameters is shrunken which reduces gradient computations and the dimensionality of the model's optimization space.
Interspace Pruning: Using Adaptive Filter Representations to Improve Training of Sparse CNNs
Finally, we show that advances of IP are due to improved trainability and superior generalization ability.
Improving the Sample-Complexity of Deep Classification Networks with Invariant Integration
We demonstrate the improved sample complexity on the Rotated-MNIST, SVHN and CIFAR-10 datasets where rotation-invariant-integration-based Wide-ResNet architectures using monomials and weighted sums outperform the respective baselines in the limited sample regime.
A Survey on Assessing the Generalization Envelope of Deep Neural Networks: Predictive Uncertainty, Out-of-distribution and Adversarial Samples
This survey connects the three fields within the larger framework of investigating the generalization performance of machine learning methods and in particular DNNs.
Boosting Deep Neural Networks with Geometrical Prior Knowledge: A Survey
One promising approach, inspired by the success of convolutional neural networks in computer vision tasks, is to incorporate knowledge about symmetric geometrical transformations of the problem to solve that affect the output in a predictable way.
GraN: An Efficient Gradient-Norm Based Detector for Adversarial and Misclassified Examples
Deep neural networks (DNNs) are vulnerable to adversarial examples and other data perturbations.
Invariant Integration in Deep Convolutional Feature Space
In this contribution, we show how to incorporate prior knowledge to a deep neural network architecture in a principled manner.
SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional Images
Omnidirectional cameras offer great benefits over classical cameras wherever a wide field of view is essential, such as in virtual reality applications or in autonomous robots.
