50 citations · 84 across the 10 of their papers we have counts for
3 papers · 1 filter
PRIME: A few primitives can boost robustness to common corruptions
Apostolos Modas, Rahul Rade, Guillermo Ortiz-Jiménez +2
Despite their impressive performance on image classification tasks, deep networks have a hard time generalizing to unforeseen corruptions of their data. To fix this vulnerability,…
A neural anisotropic view of underspecification in deep learning
Guillermo Ortiz-Jimenez, Itamar Franco Salazar-Reque, Apostolos Modas +2
The underspecification of most machine learning pipelines means that we cannot rely solely on validation performance to assess the robustness of deep learning systems to naturally…
Improving filling level classification with adversarial training
Apostolos Modas, Alessio Xompero, Ricardo Sanchez-Matilla +2
We investigate the problem of classifying - from a single image - the level of content in a cup or a drinking glass. This problem is made challenging by several ambiguities caused…