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

2026-05-17

AI Summary

This work addresses the hard-class reliability problem (HCRP) in object detection, where long-tailed minority classes consistently fail in critical scenarios. To tackle this, the authors propose ED-CCF, a decision-level inference framework that reformulates output fusion into an auditable and statistically guaranteed paradigm. ED-CCF introduces a four-state error classification scheme and a class-conditional dynamic calibration mechanism, which activates a calibration pathway only when sufficient empirical evidence is available to precisely correct hard-class errors. By integrating Bonferroni-corrected Wilcoxon significance tests with a Pareto-optimality preservation strategy, ED-CCF achieves a 22.4% improvement in mAP50 for the critical vulnerable class cz (from 0.089 to 0.109) on a 600-image benchmark, while slightly increasing the overall mAP50 to 0.585. Across 50 subset trials, it attains a 96% win rate (p<0.05), significantly enhancing robustness without compromising performance on dominant classes.

Abstract

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.

Problem

• Hard-Category Reliability Problem
• long-tail minority classes
• object detection
• catastrophic failures
• statistically guaranteed robustness

Innovation

• Error-Decomposed Class-Conditional Fusion
• Hard-Category Reliability Problem
• quad-state error taxonomy
• statistically guaranteed fusion
• Pareto optimality preservation