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

TL;DR

This paper introduces enhanced QUBO formulations for object detection suppression that incorporate appearance and confidence features, significantly improving detection accuracy in crowded scenes without increasing runtime.

Contribution

It proposes novel QUBO formulations that better distinguish occlusion from redundancy by integrating appearance similarity and confidence scores, advancing the state-of-the-art in suppression methods.

Findings

Achieved up to 4.54 points improvement in mAP.

Gained 9.89 points in mAR.

No notable increase in runtime.

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.