2.2k citations · 10.5k across the 216 of their papers we have counts for
6 papers · 1 filter
Optimising for Interpretability: Convolutional Dynamic Alignment Networks
Moritz Böhle, Mario Fritz, Bernt Schiele
We introduce a new family of neural network models called Convolutional Dynamic Alignment Networks (CoDA Nets), which are performant classifiers with a high degree of inherent inte…
Towards Reverse-Engineering Black-Box Neural Networks
Seong Joon Oh, Max Augustin, Bernt Schiele +1
Many deployed learned models are black boxes: given input, returns output. Internal information about the model, such as the architecture, optimisation procedure, or training data,…
Loss Functions for Top-k Error: Analysis and Insights
Maksim Lapin, Matthias Hein, Bernt Schiele
In order to push the performance on realistic computer vision tasks, the number of classes in modern benchmark datasets has significantly increased in recent years. This increase i…
Top-k Multiclass SVM
Maksim Lapin, Matthias Hein, Bernt Schiele
Class ambiguity is typical in image classification problems with a large number of classes. When classes are difficult to discriminate, it makes sense to allow k guesses and evalua…
Efficient Output Kernel Learning for Multiple Tasks
Pratik Jawanpuria, Maksim Lapin, Matthias Hein +1
The paradigm of multi-task learning is that one can achieve better generalization by learning tasks jointly and thus exploiting the similarity between the tasks rather than learnin…
Learning Using Privileged Information: SVM+ and Weighted SVM
Maksim Lapin, Matthias Hein, Bernt Schiele
Prior knowledge can be used to improve predictive performance of learning algorithms or reduce the amount of data required for training. The same goal is pursued within the learnin…