40 citations · 83 across the 7 of their papers we have counts for
3 papers · 1 filter
Catastrophic overfitting can be induced with discriminative non-robust features
Guillermo Ortiz-Jiménez, Pau de Jorge, Amartya Sanyal +5
Adversarial training (AT) is the de facto method for building robust neural networks, but it can be computationally expensive. To mitigate this, fast single-step attacks can be use…
On the Road to Online Adaptation for Semantic Image Segmentation
Riccardo Volpi, Pau de Jorge, Diane Larlus +1
We propose a new problem formulation and a corresponding evaluation framework to advance research on unsupervised domain adaptation for semantic image segmentation. The overall goa…
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training
Pau de Jorge, Adel Bibi, Riccardo Volpi +4
Recently, Wong et al. showed that adversarial training with single-step FGSM leads to a characteristic failure mode named Catastrophic Overfitting (CO), in which a model becomes su…