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

TL;DR

This paper introduces ED-CCF, a novel framework that improves robustness in object detection for critical minority classes without sacrificing overall performance, using a statistically validated, error-decomposed fusion approach.

Contribution

It presents a new decision-layer inference method that dynamically calibrates predictions based on a quad-state error taxonomy, addressing the Hard-Category Reliability Problem.

Findings

Achieved a 22.4% relative increase in mAP50 for the critical class cz.

Preserved and slightly improved overall detection performance across all classes.

Demonstrated 96% win rate and statistical significance across 50 trials.

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.