Abstract
RGB cameras excel at capturing rich texture details with high spatial resolution, whereas event cameras offer exceptional temporal resolution and a high dynamic range (HDR). Leveraging their complementary strengths can substantially enhance object tracking under challenging conditions, such as high-speed motion, HDR environments, and dynamic background interference. However, a significant spatio-temporal asymmetry exists between these two modalities due to their fundamentally different imaging mechanisms, hindering effective multi-modal integration. To address this issue, we propose {Hierarchical Asymmetric Distillation} (HAD), a multi-modal knowledge distillation framework that explicitly models and mitigates spatio-temporal asymmetries. Specifically, HAD proposes a hierarchical alignment strategy that minimizes information loss while maintaining the student network's computational efficiency and parameter compactness. Extensive experiments demonstrate that HAD consistently outperforms state-of-the-art methods, and comprehensive ablation studies further validate the effectiveness and necessity of each designed component. The code will be released soon.
Abstract (translated)
RGB相机擅长捕捉高空间分辨率的丰富纹理细节，而事件相机则提供卓越的时间分辨率和高动态范围（HDR）。利用这两种模态互补的优势可以显著增强在高速运动、HDR环境以及动态背景干扰等挑战条件下物体跟踪的效果。然而，由于它们的基本成像机制不同，这两种模式之间存在明显的时空不对称性，这阻碍了有效的多模态融合。为解决这一问题，我们提出了分层非对称蒸馏（Hierarchical Asymmetric Distillation, HAD），这是一个多模态知识蒸馏框架，它明确地建模和减轻了时空不对称性。具体而言，HAD提出了一种层次化对齐策略，在保持学生网络计算效率和参数精简的同时最小化信息损失。 大量的实验表明，HAD在各种基准测试中始终优于当前最先进的方法，并且全面的消融研究进一步验证了每个设计组件的有效性和必要性。代码即将发布。
URL
https://arxiv.org/abs/2510.19560
