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

arXiv: https://arxiv.org/abs/2605.17591 · HTML: https://mlsanity.com/paper/2605.17591/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 28 references that are in the map.
- First posted on arXiv 17 May 2026.

## Builds on (most cited first, 9 of 9)

- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [Frustratingly Simple Few-Shot Object Detection](https://mlsanity.com/paper/2003.06957/) (2020)
- [Long-Tailed Anomaly Detection with Learnable Class Names](https://mlsanity.com/paper/2403.20236/) (2024)
- [On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines](https://mlsanity.com/paper/2405.20459/) (2024)
- [Beyond Classification: Definition and Density-based Estimation of Calibration in Object Detection](https://mlsanity.com/paper/2312.06645/) (2023)
- [Fractal Calibration for long-tailed object detection](https://mlsanity.com/paper/2410.11774/) (2024)
- [SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection](https://mlsanity.com/paper/2412.20047/) (2024)
- [YOLO-FDA: Integrating Hierarchical Attention and Detail Enhancement for Surface Defect Detection](https://mlsanity.com/paper/2506.21135/) (2025)
- [Improving Long-Tailed Object Detection with Balanced Group Softmax and Metric Learning](https://mlsanity.com/paper/2511.16619/) (2025)

## Abstract (arXiv)

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.