A prototype-based variational autoencoder with a generalized-Gaussian restriction loss and perceptual reconstruction detects out-of-distribution images better than prior methods on some benchmarks, especially low-diversity datasets.
In: CVPR Work- shops
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enclosing Prototypical Variational Autoencoder for Explainable Out-of-Distribution Detection
A prototype-based variational autoencoder with a generalized-Gaussian restriction loss and perceptual reconstruction detects out-of-distribution images better than prior methods on some benchmarks, especially low-diversity datasets.