1 code implementation • 26 Jan 2023 • Hyeongji Kim, Pekka Parviainen, Terje Berge, Ketil Malde
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.
no code implementations • 2 Jan 2023 • Ørjan Langøy Olsen, Tonje Knutsen Sørdalen, Morten Goodwin, Ketil Malde, Kristian Muri Knausgård, Kim Tallaksen Halvorsen
In both terrestrial and marine ecology, physical tagging is a frequently used method to study population dynamics and behavior.
1 code implementation • 21 Jan 2022 • Hyeongji Kim, Pekka Parviainen, Ketil Malde
We propose a distance-ratio-based (DR) formulation for metric learning.
no code implementations • 28 Sep 2020 • Hyeongji Kim, Ketil Malde
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.
1 code implementation • 6 May 2020 • Hyeongji Kim, Pekka Parviainen, Ketil Malde
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.
no code implementations • 25 Sep 2019 • Ketil Malde, Hyeongji Kim
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.