HAD: Hierarchical Asymmetric Distillation to Bridge Spatio-Temporal Gaps in Event-Based Object Tracking
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909864042692608 |
|---|---|
| author | Deng, Yao Zhong, Xian Liu, Wenxuan Yu, Zhaofei Yuan, Jingling Huang, Tiejun |
| author_facet | Deng, Yao Zhong, Xian Liu, Wenxuan Yu, Zhaofei Yuan, Jingling Huang, Tiejun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_19560 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HAD: Hierarchical Asymmetric Distillation to Bridge Spatio-Temporal Gaps in Event-Based Object Tracking Deng, Yao Zhong, Xian Liu, Wenxuan Yu, Zhaofei Yuan, Jingling Huang, Tiejun Computer Vision and Pattern Recognition 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. |
| title | HAD: Hierarchical Asymmetric Distillation to Bridge Spatio-Temporal Gaps in Event-Based Object Tracking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.19560 |