SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness
Jindong Gu, Hengshuang Zhao, Volker Tresp, Philip H. S. Torr
Topics & Concepts
Adversarial systemComputer scienceSegmentationRobustness (evolution)Artificial intelligenceBoosting (machine learning)Machine learningDeep neural networksImage segmentationArtificial neural networkPattern recognition (psychology)GeneChemistryBiochemistryAdversarial Robustness in Machine Learning