Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Luca Marson"'
Publikováno v:
ICPR
This paper presents a new approach to the problem of detecting out-of-distribution (OOD) inputs in image classifications with deep convolutional networks. We leverage so-called boundary samples to enforce low confidence (maximum softmax probabilities
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0830a1d815231f84c93cf7a4180be15b
https://doi.org/10.1109/icpr48806.2021.9412612
https://doi.org/10.1109/icpr48806.2021.9412612
