冻结行人检测器的监督后处理选择:信息、目标变化与完整成本分析
Choosing Supervised Post-Processing for Frozen Person Detectors: Information, Object Changes, and Complete Cost
AI 导读
该研究比较了冻结行人检测器多种监督后处理读出方案,在 320 张 CrowdHuman 留出图像上,向 97 维读出加入 native-set 上下文可多获得 275 个匹配和 96 个未匹配预测;319 图像队列中 Full100 匹配 6004 个目标,高于原始 WBF 的 5848。
正文 · 原文
Abstract:A frozen detector computes hypotheses that can support better final outputs through supervised post-processing. Choosing a readout requires knowing which available information improves detection and what its processing costs. We compare candidate scores, class distributions, geometry, native-set summaries and adapted neighborhood meta classification under common candidate, supervision and operating-point conditions. On 320 held-out CrowdHuman images, adding native-set context to a 97-dimensional readout yields 275 more matches and 96 more unmatched predictions. On a separate 319-image cohort, Full100 matches 6004 objects,versus 5848 for source-selected raw WBF and 6002 for a MetaDetect-style adaptation. Its gain over raw contains 300 added and 144 lost discoveries. After execution-equivalent optimization, Full100 and the meta-statistics readout both take approximately 95 ms per complete warm request on a fixed 64-image workload. Source-frozen transfer gives positive point results on 223 MOT17Det frames from seven sequences, while the main MIAP result shows no improvement. The study supports using sufficiently informative output readouts while retaining optimized meta classification as a competitive option. It also shows why feature dimension and net detection gain alone are unreliable guides to adoption.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.24003 [cs.CV] |
| (or arXiv:2611.24003v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.24003 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zijun Jia [view email]
[v1]
Wed, 18 Nov 2026 07:53:06 UTC (366 KB)
来源:arXiv cs.AI · arxiv.org