发表机构
Beijing Institute of Technology（北京理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有多光谱检测器的三类局限，提出FressDet框架，通过三个互补组件实现任意平面旋转下的可靠光谱-空间融合，在参数量减少93%的情况下取得SOTA性能。
AI 中文摘要
现有多光谱检测器受限于离散光谱处理、光谱与空间线索的相对可靠性在金字塔层级间存在依尺度偏移的问题，且缺乏针对任意朝向目标的显式旋转等变几何先验。为解决这些局限，本文提出FressDet，一种面向多光谱目标检测的完全旋转等变光谱-空间学习框架，能够捕捉光谱结构的连续有序特性，并在任意平面旋转下实现跨金字塔层级的可靠光谱-空间融合。FressDet集成三个互补组件：光谱隐式变形（SpeIW）通过坐标条件隐式场实现基于查询的光谱重采样，生成单调保序的变形；旋转等变一致性加权（ReCoW）基于分支可靠性自适应融合光谱与空间分支，在跨金字塔层级强化有效线索的同时抑制噪声；朝向感知检测头利用组索引特征，无需参数复制即可稳定预测朝向目标。综上，即便在旋转扰动下，FressDet也能学习到更具判别性与鲁棒性的光谱-空间表示。该模型在三个公开基准上以少93%的参数量取得了当前最优性能，证明了其有效性与泛化性。
英文摘要
Existing multispectral detectors are limited by discrete spectral processing, a scale-dependent shift in the relative reliability of spectral and spatial cues across pyramid levels, and the lack of explicit rotation-equivariant geometric priors for arbitrarily oriented objects. To tackle these limitations, we propose FressDet, a fully rotation-equivariant spectral-spatial learning framework for multispectral object detection, capable of capturing the continuous, ordered nature of spectral structure and enabling reliable spectral-spatial fusion across pyramid levels under arbitrary in-plane rotations. FressDet integrates three complementary components. Spectral Implicit Warp (SpeIW) enables query-based spectral resampling via a coordinate-conditioned implicit field, yielding a monotone, order-preserving warp. Rotation-Equivariant Consistency Weighting (ReCoW) adaptively fuses spectral and spatial branches based on branch reliability, reinforcing informative cues while suppressing noise across pyramid levels. The oriented-aware head exploits group-indexed features to stably predict oriented objects without parameter replication. Taken together, FressDet learns more discriminative and robust spectral-spatial representations even under rotational perturbations. By achieving state-of-the-art performance with 93% fewer parameters on five public benchmarks, FressDet demonstrates its effectiveness and generalizability.
CommentsAccepted by ECCV 2026
