论文标题
实例细分模型的鲁棒性评估和对抗性培训
Robustness Evaluation and Adversarial Training of an Instance Segmentation Model
论文作者
论文摘要
为了评估非分类器模型的鲁棒性，我们根据随机平滑的概念提出了概率的局部等效性，以定量评估任意函数的鲁棒性。此外，为了了解对抗性训练对非分类群的影响，并研究可以在不降低培训分布上降低性能的情况下获得的鲁棒性水平，我们快速应用比免费的对抗性培训以及对实例段网络的培训的贸易损失更好。在这个方向上，我们能够在Tusimple Lane检测挑战上获得对称最佳骰子得分0.85，表现优于标准训练的网络的得分为0.82。此外，与标准训练的网络的得分为0相比，我们能够获得0.49的F量表。我们表明，概率的局部等效性能够成功地区分标准训练和对抗性训练的模型，从而提供了对对抗性模型的强大鲁棒性的另一种观点。
To evaluate the robustness of non-classifier models, we propose probabilistic local equivalence, based on the notion of randomized smoothing, as a way to quantitatively evaluate the robustness of an arbitrary function. In addition, to understand the effect of adversarial training on non-classifiers and to investigate the level of robustness that can be obtained without degrading performance on the training distribution, we apply Fast is Better than Free adversarial training together with the TRADES robust loss to the training of an instance segmentation network. In this direction, we were able to achieve a symmetric best dice score of 0.85 on the TuSimple lane detection challenge, outperforming the standardly-trained network's score of 0.82. Additionally, we were able to obtain an F-measure of 0.49 on manipulated inputs, in contrast to the standardly-trained network's score of 0. We show that probabilisitic local equivalence is able to successfully distinguish between standardly-trained and adversarially-trained models, providing another view of the improved robustness of the adversarially-trained models.
