Single-point supervised infrared small target detection (IRSTD) drastically reduces dense annotation costs. Current state-of-the-art (SOTA) methods achieve high precision by recovering mask supervision through explicit, offline pseudo-label construction, such as multi-stage active learning and physics-driven mask generation. In this paper, we study a minimalist alternative: generating point-to-mask supervision online through in-batch, point-anchored feature-affinity propagation. We instantiate this paradigm as GSACP, an end-to-end testbed that directly supervises the detector using hard-margin feature affinity gated by local image priors, entirely eliminating external label-evolution loops. This compact design, however, exposes an optimization bottleneck. Because the affinity target is generated from the same feature representation being optimized, training forms a self-referential loop. We theoretically formalize this as \emph{Self-Referential Propagation Drift}, a representation-supervision entanglement that can sharpen true boundaries or distort the feature space to satisfy its own targets. To systematically isolate these failure modes, we apply a protocolized single-variable ablation procedure spanning local EMA teacher decoupling, hard-background contrastive separation, and adaptive support geometry. On the SIRST3 dataset, GSACP-Final establishes a new ultra-low false-alarm operating regime, achieving a highly competitive $0.6674$ mIoU while demonstrating a $38\% relative reduction in false-positive artifacts ($\mathrm{Fa}$) compared with PAL. By systematically deconstructing the end-to-end paradigm, we map its performance boundaries and show that in-batch feature propagation provides a compact alternative for deployment scenarios where false-alarm suppression is paramount.

翻译：单点监督红外小目标检测（IRSTD）大幅降低了密集标注成本。当前最先进的（SOTA）方法通过显式、离线伪标签构建（例如多阶段主动学习和物理驱动的掩码生成）恢复掩码监督，实现了高精度。本文研究了一种极简替代方案：通过批内、点锚定特征亲和传播在线生成点到掩码监督。我们将这一范式实例化为GSACP——一个端到端测试平台，通过由局部图像先验门控的硬间隔特征亲和度直接监督检测器，完全消除了外部标签演化循环。然而，这种紧凑设计暴露了一个优化瓶颈：由于亲和目标由同一特征表示生成并参与优化，训练形成了自参照循环。我们将其理论化为**自参照传播漂移**，这是一种表示-监督纠缠现象，可能锐化真实边界或扭曲特征空间以迎合自身目标。为系统隔离这些失效模式，我们采用协议化的单变量消融过程，涵盖局部EMA教师解耦、硬背景对比分离和自适应支撑几何。在SIRST3数据集上，GSACP-Final建立了新的超低虚警工作区间，实现了极具竞争力的0.6674 mIoU，同时与PAL相比，虚警伪影（Fa）相对降低了38%。通过系统解构端到端范式，我们映射了其性能边界，并表明批内特征传播为虚警抑制至关重要的部署场景提供了紧凑替代方案。