研究人员开发了GSACP，一种用于单点监督红外小目标检测的新型端到端方法。该方法通过特征亲和性传播在线生成监督信号，无需复杂的离线伪标签构建。虽然这种设计引入了自指优化挑战，但GSACP-Final在SIRST3数据集上显著减少了误报并取得了有竞争力的性能。 AI
影响 为红外小目标检测提供了一种更紧凑、更有效的方法，尤其是在误报最小化至关重要的场景中。
排序理由 关于红外小目标检测新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
新的GSACP方法通过特征亲和性传播改进红外小目标检测
报道来源 [2]
-
Exploring the Limits of End-to-End Feature-Affinity Propagation for Single-Point Supervised Infrared Small Target Detection
arXiv:2605.00722v1 Announce Type: new Abstract: 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 pseu…
-
Exploring the Limits of End-to-End Feature-Affinity Propagation for Single-Point Supervised Infrared Small Target Detection
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 activ…