Adversarial attacks have been recently investigated in person re-identification. These attacks perform well under cross dataset or cross model setting. However, the challenges present in cross-dataset cross-model scenario does not allow these models to achieve similar accuracy. To this end, we propose our method with the goal of achieving better transferability against different models and across datasets. We generate a mask to obtain better performance across models and use meta learning to boost the generalizability in the challenging cross-dataset cross-model setting. Experiments on Market-1501, DukeMTMC-reID and MSMT-17 demonstrate favorable results compared to other attacks.
翻译:最近对反versari攻击进行了面对面重新识别调查,这些攻击在交叉数据集或交叉模型设置下表现良好,不过,交叉数据集跨模型设想中存在的挑战使这些模型无法达到类似的准确性。为此目的,我们提出我们的方法,目的是针对不同的模型和跨数据集实现更好的可转移性。我们制作了一个面具,以获得更好的不同模型的性能,并利用元学习来提高具有挑战性的交叉数据集跨模型设置的通用性。在市场1501、杜克MTMC-reID和MSMT-17上进行的实验显示了与其他攻击相比的有利结果。