arXiv:2605.17591cs.CV2026-05

针对少数类别检测失效问题,提出可精准修复且不损整体性能的新融合方法。

Error-Decomposed Class-Conditional Fusion for Statistically Guaranteed Hard-Category Robust Perception

论文配图:Error-Decomposed Class-Conditional Fusion for Statistically Guaranteed Hard-Category Robust Perception
图 1 · 摘自论文原文
  • 在决策层构建四状态误差分类,仅在证据充分时触发校准
  • 少数类mAP50提升22.4%至0.109,全局性能几乎无损
  • 适用于高安全要求的视觉感知场景,如自动驾驶

现有目标检测指标掩盖了长尾少数类别在实际应用中的灾难性、重复性失败。本文首次将此普遍缺陷定义为硬类别可靠性问题(HCRP):在严格协议下,必须彻底修复脆弱类别,同时不损害稳定类别的性能边界。为此提出误差分解的类别条件融合(ED-CCF),一种决策层推理框架。不同于启发式全局后处理,ED-CCF将预测投影至复杂四状态误差分类,仅在充分实证支持下动态激活校准路径。在600图像严格验证基准上,识别cz为关键脆弱类别(HCEC=0.86,BSR=0.14),本框架实现针对性突破:cz mAP50从0.089343提升至0.109353(相对增长22.4%),同时全局mAP50从0.581925升至0.584864,完美保持帕累托最优。经50组配对子集试验验证,胜率高达96%,且经邦弗隆校正的威尔科克森检验显著(p<0.05)。该工作从根本上将输出级融合重构为可审计、统计保证的安全关键视觉感知范式。

原文摘要 · Abstract (English)

Aggregate object detection metrics inherently mask catastrophic and repeatable failures in operationally critical, long-tail minority classes. This paper formally defines this pervasive vulnerability as the Hard-Category Reliability Problem (HCRP): the fundamental architectural challenge of strictly rectifying vulnerable categories without compromising the performance boundaries of stable classes under stringent protocols. To systematically dismantle this limitation, we propose Error-Decomposed Class-Conditional Fusion (ED-CCF), an elegant decision-layer inference framework. Diverging from heuristic global post-processing, ED-CCF projects predictions into a sophisticated quad-state error taxonomy, dynamically activating calibration pathways exclusively upon rigorous empirical justification. On a highly constrained 600-image validation benchmark, isolating cz as the critical vulnerability (HCEC=0.86, BSR=0.14), our framework achieves a targeted breakthrough: it elevates cz mAP50 from 0.089343 to 0.109353 (a massive +22.4% relative surge) while flawlessly preserving the Pareto optimality of global stability (raising all mAP50 from 0.581925 to 0.584864). Backed by exhaustive validation across 50 paired subset trials demonstrating an overwhelming 96% win rate and strict Bonferroni-corrected Wilcoxon significance (p<0.05), this work fundamentally redefines output-level fusion as an auditable, statistically guaranteed paradigm for safety-critical visual perception.

目标检测鲁棒性长尾分布安全感知

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。