根据复杂度动态调整光谱特征提取能力，提升多光谱目标追踪精度与效率。
SpecTrack: Spectral Prompt Guided Adaptive Experts for Multispectral Object Tracking
- 按搜索区域难易程度自适应分配光谱-空间处理能力，核心是分层专家模块与光谱提示路由。
- 在MUST、MSITrack、HOTC20上分别取得65.2%、51.9%、72.6% AUC，平衡版达43.7 FPS。
- 适合需要高鲁棒性多光谱追踪的场景，尤其光照变化大或背景干扰强的任务。
多光谱图像（MSI）和高光谱图像（HSI）目标追踪利用波段级观测提升在相似RGB外观、混合像素、光照变化、遮挡和杂乱环境下的目标-背景区分能力。然而，现有追踪器通常以固定容量的光谱-空间路径处理所有搜索区域，忽视了帧间与目标状态间的追踪难度差异。清晰区域仅需轻量局部判别，而模糊边界与光谱相似干扰物则需更强上下文推理。为此，我们提出SpecTrack，一种面向光谱-空间复杂度感知的追踪器，将MSI追踪建模为搜索区域级别的自适应容量分配问题。其核心组件——光谱自适应专家混合（SAMoE）模块，提供渐进式增加隐空间秩、感受野与深度的专家池。专家选择由光谱提示路由机制引导，融合语义上下文、空间边界线索及多光谱块嵌入后的通道变化隐含信号，为每个搜索区域激活稀疏专家子集。同时，共享全局专家提供通用的光谱-空间上下文，减少碎片化路由决策。在MUST、MSITrack和HOTC20上的实验表明，该方法实现了优异的精度-效率权衡。以精度为导向的SpecTrack-L384在三个基准上分别达到65.2%、51.9%、72.6% AUC；平衡型SpecTrack-B224在MUST上实现62.4% AUC，运行速度达43.7 FPS。额外在GOT-10k上的评估显示其对RGB域架构的泛化能力，SpecTrack-L384达到79.3% AO。
原文摘要 · Abstract (English)
Multispectral image(MSI) and hyperspectral image(HSI) object tracking object tracking exploits recorded band-wise observations to improve target--background discrimination under similar RGB appearance, mixed pixels, illumination variation, occlusion, and clutter. However, existing trackers commonly process all search regions through a fixed capacity spectral--spatial path, ignoring that tracking difficulty varies substantially across frames and target states. Clear regions may require only lightweight local discrimination, whereas ambiguous boundaries and spectrally similar distractors often demand stronger contextual reasoning. To address this limitation, we propose SpecTrack, a spectral--spatial complexity-aware tracker that formulates MSI tracking as search-region-level adaptive capacity allocation. Its core component, the Spectral Adaptive Mixture-of-Experts (SAMoE) module, provides a capacity-ordered expert pool with progressively increasing latent rank, receptive field, and depth. Expert selection is guided by a Spectral Prompt Router, which fuses semantic context, spatial boundary cues, and a latent channel-variation cue computed after multispectral patch embedding to activate a sparse subset of SAMoE experts for each search region. In parallel, a Shared Global Expert supplies common latent spectral--spatial context to reduce fragmented sparse-routing decisions. Experiments on MUST, MSITrack, and HOTC20 demonstrate a favorable accuracy--efficiency trade-off. The accuracy-oriented SpecTrack-L384 achieves state-of-the-art or highly competitive AUCs of 65.2\%, 51.9\%, and 72.6\% on the three benchmarks, while the balanced SpecTrack-B224 reaches 62.4\% AUC at 43.7 FPS on MUST. An additional GOT-10k evaluation indicates RGB-domain architectural generalization, with SpecTrack-L384 achieving 79.3\% AO.
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。