SiamABC提升视觉追踪泛化能力，可在资源受限下实时运行。
Improving Accuracy and Generalization for Efficient Visual Tracking
- 采用新架构与损失函数，增强对目标动态变化的适应性。
- 在OOD数据集上比MixFormerV2-S高7.6%准确率，且速度达100FPS。
- 支持无需反向传播的快速测试时自适应，适合真实场景部署。
高效视觉追踪器在训练分布内表现良好，但在分布外序列上泛化能力差，限制了其在真实环境中的应用。本文提出SiamABC，一种高效孪生追踪器，在保持高精度的同时显著提升对分布外（OOD）序列的泛化能力。该方法通过新颖的网络结构设计，更好地捕捉目标的动态变化，并引入新的训练损失。此外，它直接解决泛化问题，采用无需反向传播的快速测试时动态自适应机制，持续根据目标视觉变化调整模型。大量实验表明，SiamABC在分布外基准（如AVisT）上性能显著优于现有方法，相比MixFormerV2-S提升7.6%，且在CPU上达到100帧/秒，速度提升3倍。代码与模型已公开于https://wvuvl.github.io/SiamABC/。
原文摘要 · Abstract (English)
Efficient visual trackers overfit to their training distributions and lack generalization abilities, resulting in them performing well on their respective in-distribution (ID) test sets and not as well on out-of-distribution (OOD) sequences, imposing limitations to their deployment in-the-wild under constrained resources. We introduce SiamABC, a highly efficient Siamese tracker that significantly improves tracking performance, even on OOD sequences. SiamABC takes advantage of new architectural designs in the way it bridges the dynamic variability of the target, and of new losses for training. Also, it directly addresses OOD tracking generalization by including a fast backward-free dynamic test-time adaptation method that continuously adapts the model according to the dynamic visual changes of the target. Our extensive experiments suggest that SiamABC shows remarkable performance gains in OOD sets while maintaining accurate performance on the ID benchmarks. SiamABC outperforms MixFormerV2-S by 7.6\% on the OOD AVisT benchmark while being 3x faster (100 FPS) on a CPU. Our code and models are available at https://wvuvl.github.io/SiamABC/.
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。