Enhancing Quantum-ready QUBO-based Suppression for Object Detection with Appearance and Confidence Features

2025-02-05

AI Summary

Traditional non-maximum suppression (NMS) often erroneously removes occluded true positives in crowded scenes, while existing Quadratic Unconstrained Binary Optimization (QUBO)-based suppression methods struggle to distinguish between occlusion-induced overlaps and redundant detections. Method: This paper proposes a novel QUBO formulation that jointly models pairwise detection scores as the product of confidence and appearance similarity—measured via cosine similarity of deep features—thereby endowing the QUBO objective with semantic discriminative capability to differentiate occlusion from redundancy. The method preserves the original QUBO framework and solver pipeline, introducing only lightweight appearance feature computation with negligible computational overhead. Contribution/Results: Evaluated on standard benchmarks, the approach achieves +4.54 mAP and +9.89 mAR improvements over prior QUBO-based methods, demonstrating the effectiveness of appearance-confidence joint modeling for preserving occluded objects.

Technology Category

• Computer Vision: Object Detection & Categorization
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Quadratic Unconstrained Binary Optimization (QUBO)-based suppression in object detection is known to have superiority to conventional Non-Maximum Suppression (NMS), especially for crowded scenes where NMS possibly suppresses the (partially-) occluded true positives with low confidence scores. Whereas existing QUBO formulations are less likely to miss occluded objects than NMS, there is room for improvement because existing QUBO formulations naively consider confidence scores and pairwise scores based on spatial overlap between predictions. This study proposes new QUBO formulations that aim to distinguish whether the overlap between predictions is due to the occlusion of objects or due to redundancy in prediction, i.e., multiple predictions for a single object. The proposed QUBO formulation integrates two features into the pairwise score of the existing QUBO formulation: i) the appearance feature calculated by the image similarity metric and ii) the product of confidence scores. These features are derived from the hypothesis that redundant predictions share a similar appearance feature and (partially-) occluded objects have low confidence scores, respectively. The proposed methods demonstrate significant advancement over state-of-the-art QUBO-based suppression without a notable increase in runtime, achieving up to 4.54 points improvement in mAP and 9.89 points gain in mAR.

Problem

• Improves QUBO-based suppression for object detection
• Distinguishes occlusion from redundant predictions
• Enhances mAP and mAR without increasing runtime

Innovation

• Integrates appearance and confidence features
• Improves QUBO formulations for object detection
• Enhances suppression in crowded scene scenarios