用扩散模型提升视觉追踪抗干扰能力，实时且效果显著。
Towards Effective and Efficient Adversarial Defense with Diffusion Models for Robust Visual Tracking
- 基于扩散模型构建多尺度去噪防御机制
- 在多个数据集上显著提升追踪性能，达30 FPS以上
- 适合需要实时鲁棒追踪的工程应用
尽管基于深度学习的视觉追踪方法取得了显著进展，但在面对精心设计的对抗攻击时仍显脆弱，导致追踪性能急剧下降。为此，本文首次提出一种基于去噪扩散概率模型的新型对抗防御方法DiffDf，旨在有效提升现有视觉追踪方法对对抗攻击的鲁棒性。DiffDf通过结合像素级重建损失、语义一致性损失和结构相似性损失，建立多尺度防御机制，利用逐步去噪过程有效抑制对抗扰动。在多个主流数据集上的大量实验表明，DiffDf对不同架构的追踪器均表现出优异的泛化性能，显著提升各项评估指标，同时实现超过30 FPS的实时推理速度，展现出卓越的防御性能与效率。代码已开源：https://github.com/pgao-lab/DiffDf。
原文摘要 · Abstract (English)
Although deep learning-based visual tracking methods have made significant progress, they exhibit vulnerabilities when facing carefully designed adversarial attacks, which can lead to a sharp decline in tracking performance. To address this issue, this paper proposes for the first time a novel adversarial defense method based on denoise diffusion probabilistic models, termed DiffDf, aimed at effectively improving the robustness of existing visual tracking methods against adversarial attacks. DiffDf establishes a multi-scale defense mechanism by combining pixel-level reconstruction loss, semantic consistency loss, and structural similarity loss, effectively suppressing adversarial perturbations through a gradual denoising process. Extensive experimental results on several mainstream datasets show that the DiffDf method demonstrates excellent generalization performance for trackers with different architectures, significantly improving various evaluation metrics while achieving real-time inference speeds of over 30 FPS, showcasing outstanding defense performance and efficiency. Codes are available at https://github.com/pgao-lab/DiffDf.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。