Search Results for author:
Found 5 papers, 3 papers with code
Inspecting class hierarchies in classification-based metric learning models
In addition to the standard classification accuracy, we evaluate the hierarchical inference performance by inspecting learned class representatives and the hierarchy-informed performance, i. e., the classification performance, and the metric learning performance by considering predefined hierarchical structures.
Distance-Ratio-Based Formulation for Metric Learning
We propose a distance-ratio-based (DR) formulation for metric learning.
Proper Measure for Adversarial Robustness
In order to handle the problems of the standard adversarial accuracy, we introduce a new measure for the robustness of classifiers called genuine adversarial accuracy.
Measuring Adversarial Robustness using a Voronoi-Epsilon Adversary
As a result, adversarial accuracy based on this adversary avoids a tradeoff between accuracy and adversarial accuracy on training data even when $\epsilon$ is large.
Beyond image classification: zooplankton identification with deep vector space embeddings
For practical cases in ecology as well as in many other fields this is not the case, and we argue that the vector embedding method presented here is a more appropriate approach.
