#ai-robustness
Read more stories on Hashnode
Articles with this tag
TL; DR by carefully selecting where to put aliasing mitigation in a CNN it is possible to limit anti-aliasing information loss. Aliasing negatively...
The last two posts (1, 2) I published were on the topic of spatial robustness, i.e. the stability of a neural network prediction with respect to small...
TL; DR Many operations in a typical convolutional neural network down-sample the signal without accounting for aliasing. Aliasing causes frequency...
TL; DR Image classification model (probably vision models in general) are spatially brittle. Small combination of rotation and translation can...
While this is an older paper (2017), it holds significant relevance in the field of robustness. The paper addresses a fundamental and still relevant...
