Gaussian Latent Representations for Uncertainty Estimation using Mahalanobis Distance in Deep Classifiers
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F23%3A00374356" target="_blank" >RIV/68407700:21730/23:00374356 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1109/ICCVW60793.2023.00483" target="_blank" >https://doi.org/10.1109/ICCVW60793.2023.00483</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICCVW60793.2023.00483" target="_blank" >10.1109/ICCVW60793.2023.00483</a>
Alternative languages
Result language
angličtina
Original language name
Gaussian Latent Representations for Uncertainty Estimation using Mahalanobis Distance in Deep Classifiers
Original language description
Recent works show that the data distribution in a network's latent space is useful for estimating classification uncertainty and detecting Out-Of-Distribution (OOD) samples. To obtain a well-regularized latent space that is conducive for uncertainty estimation, existing methods bring in significant changes to model architectures and training procedures. In this paper, we present a lightweight and high-performance regularization method for Mahalanobis distance (MD)-based uncertainty prediction, and that requires minimal changes to the network's architecture. To derive Gaussian latent representation favourable for MD calculation, we introduce a self-supervised representation learning method that separates in-class representations into multiple Gaussians. Classes with non-Gaussian representations are automatically identified and dynamically clustered into multiple new classes that are approximately Gaussian. Evaluation on standard OOD benchmarks shows that our method achieves state-of-the-art results on OOD detection and is very competitive on predictive probability calibration. Finally, we show the applicability of our method to a real-life computer vision use case on microorganism classification.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
ICCVW2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
ISBN
979-8-3503-0744-3
ISSN
2473-9936
e-ISSN
2473-9944
Number of pages
10
Pages from-to
4490-4499
Publisher name
IEEE
Place of publication
Anchorage, Alaska
Event location
Paris
Event date
Oct 2, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
001156680304062