Pixel-level Quality Assessment for Oriented Object Detection

TL;DR

This paper introduces Pixel-level Quality Assessment (PQA), a novel method for more accurately estimating localization quality in oriented object detection by analyzing pixel-level spatial consistency, outperforming traditional box-level IoU prediction.

Contribution

The paper proposes PQA, a pixel-level approach that overcomes box-level IoU prediction limitations, providing a more precise localization quality measure for oriented object detectors.

Findings

PQA improves detection performance on HRSC2016 and DOTA datasets.

PQA enhances AP metrics in various oriented object detectors.

PQA seamlessly integrates with existing detectors, boosting accuracy.

Abstract

Modern oriented object detectors typically predict a set of bounding boxes and select the top-ranked ones based on estimated localization quality. Achieving high detection performance requires that the estimated quality closely aligns with the actual localization accuracy. To this end, existing approaches predict the Intersection over Union (IoU) between the predicted and ground-truth (GT) boxes as a proxy for localization quality. However, box-level IoU prediction suffers from a structural coupling issue: since the predicted box is derived from the detector's internal estimation of the GT box, the predicted IoU--based on their similarity--can be overestimated for poorly localized boxes. To overcome this limitation, we propose a novel Pixel-level Quality Assessment (PQA) framework, which replaces box-level IoU prediction with the integration of pixel-level spatial consistency. PQA measures the alignment between each pixel's relative position to the predicted box and its corresponding position to the GT box. By operating at the pixel level, PQA avoids directly comparing the predicted box with the estimated GT box, thereby eliminating the inherent similarity bias in box-level IoU prediction. Furthermore, we introduce a new integration metric that aggregates pixel-level spatial consistency into a unified quality score, yielding a more accurate approximation of the actual localization quality. Extensive experiments on HRSC2016 and DOTA demonstrate that PQA can be seamlessly integrated into various oriented object detectors, consistently improving performance (e.g., +5.96% AP$_{50:95}$ on Rotated RetinaNet and +2.32% on STD).