利用辅助对抗防御网络增强跟踪鲁棒性
Enhancing Tracking Robustness with Auxiliary Adversarial Defense Networks
AI总结：
针对视觉跟踪缺乏对抗防御的问题，提出即插即用预处理网络 AADN，通过 Dua-Loss 对抗训练增强鲁棒性，并在多个基准上验证其防御效果、可迁移性和实时性。
摘要：
视觉目标跟踪中的对抗攻击通过向图像中引入难以察觉的扰动，显著降低了先进跟踪器的性能。然而，目前仍缺乏针对目标跟踪设计对抗防御方法的研究。为解决这些问题，我们提出了一种有效的辅助预处理防御网络 AADN，该网络在将输入图像送入跟踪器之前对其执行防御性变换。此外，它可以作为即插即用模块与其他视觉跟踪器无缝集成，无需调整参数。我们使用对抗训练来训练 AADN，具体采用 Dua-Loss 生成对抗样本，这些样本同时攻击跟踪器的分类分支和回归分支。在 OTB100、LaSOT 和 VOT2018 基准上进行的大量实验表明，在自适应和非自适应攻击场景下，AADN 对对抗攻击方法均保持出色的防御鲁棒性。此外，当将该防御网络迁移到异构跟踪器时，它表现出可靠的可迁移性。最后，AADN 实现了高达 5 毫秒/帧的处理速度，可与现有高速跟踪器无缝集成，而不会引入显著的计算开销。
英文摘要：
Adversarial attacks in visual object tracking have significantly degraded the performance of advanced trackers by introducing imperceptible perturbations into images. However, there is still a lack of research on designing adversarial defense methods for object tracking. To address these issues, we propose an effective auxiliary pre-processing defense network, AADN, which performs defensive transformations on the input images before feeding them into the tracker. Moreover, it can be seamlessly integrated with other visual trackers as a plug-and-play module without parameter adjustments. We train AADN using adversarial training, specifically employing Dua-Loss to generate adversarial samples that simultaneously attack the classification and regression branches of the tracker. Extensive experiments conducted on the OTB100, LaSOT, and VOT2018 benchmarks demonstrate that AADN maintains excellent defense robustness against adversarial attack methods in both adaptive and non-adaptive attack scenarios. Moreover, when transferring the defense network to heterogeneous trackers, it exhibits reliable transferability. Finally, AADN achieves a processing time of up to 5ms/frame, allowing seamless integration with existing high-speed trackers without introducing significant computational overhead.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
