Matteo Saponati
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper identifies a linear predictive law linking the initial performance gap in on-policy self-distillation (OPSD) to the final performance improvement, allowing researchers to anticipate and tune OPSD outcomes before full training.
The paper proposes combining Gaussian noise and bilateral filtering into a simple preprocessor that achieves supralinear and scalable adversarial robustness in CNNs with significantly reduced computational overhead compared to state-of-the-art methods.
Papers
A combination of noise and bilateral filters achieve supralinear and scalable adversarial robustness in CNNs
The paper proposes combining Gaussian noise and bilateral filtering into a simple preprocessor that achieves supralinear and scalable adversarial robustness in CNNs with significantly reduced computat…