FSLoRA：通过频域-空间低秩适配器协调检测与重识别实现单阶段行人搜索
FSLoRA: Harmonizing Detection and Re-Identification via Freq-Spatial Low-Rank Adapter for One-Stage Person Search
把 LoRA 与混合专家结合成骨干网络级的即插即用适配器，并在频域上做任务相关分量的选择性增强，为单阶段检测+重识别这类多任务特征纠缠问题提供了可复用的解耦手段。
原文依据 we propose FSLoRA, a Freq-Spatial Low-Rank Adapter that progressively decouples task-specific features at the backbone level
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论行人搜索旨在无约束场景中检测并重识别个体，而单阶段模型面临一个内在冲突：行人检测关注共享的人体特征，而行人重识别需要身份特定的表征。现有方法如特征解耦与损失重加权，主要在网络后段处理该问题，却未能解决早期阶段的特征纠缠。为克服这一局限，我们提出 FSLoRA，一种频域-空间低秩适配器，在骨干网络层面渐进地解耦任务特定特征。FSLoRA 由空间级模块（SLM）与频率级模块（FLM）组成：前者利用低秩适配与混合专家动态激活任务相关的空间特征，后者将特征变换到频域，以选择性增强任务相关的频率分量并抑制任务无关的噪声。通过整合空间与频率两种自适应，FSLoRA 减少了特征干扰，使联合优化更为有效。在 CUHK-SYSU、PRW 与 Posetrack21 上的大量实验表明，FSLoRA 不仅取得了最优性能，还可作为即插即用模块适配多种行人搜索框架，为单阶段行人搜索提供了统一且可泛化的解决方案。
英文原文摘要 1369 字符
Person search, which aims to detect and re-identify individuals in unconstrained scenes, faces an inherent conflict in one-stage models: pedestrian detection focuses on shared human features, while person re-identification requires identity-specific representations. Existing approaches, such as feature decoupling and loss re-weighting, primarily address this issue in later network stages but fail to resolve early-stage feature entanglement. To overcome this limitation, we propose FSLoRA, a Freq-Spatial Low-Rank Adapter that progressively decouples task-specific features at the backbone level. FSLoRA consists of a Spatial-Level Module (SLM), which employs LoRA and a mixture-of-experts to dynamically activate task-relevant spatial features, and a Frequency-Level Module (FLM), which transforms features into the frequency domain to selectively enhance task-relevant frequency components while suppressing task-irrelevant noise. By integrating both spatial and frequency-based adaptations, FSLoRA reduces feature interference, enabling more effective joint optimization. Extensive experiments on CUHK-SYSU, PRW, and Posetrack21 demonstrate that FSLoRA not only achieves state-of-the-art performance but also serves as a plug-and-play module adaptable to various person search frameworks, offering a unified and generalizable solution for one-stage person search.