# Pixel-level Quality Assessment for Oriented Object Detection

arXiv: https://arxiv.org/abs/2511.08186 · HTML: https://mlsanity.com/paper/2511.08186/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 37 references that are in the map.
- First posted on arXiv 11 Nov 2025.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection](https://mlsanity.com/paper/2006.04388/) (2020)
- [VarifocalNet: An IoU-aware Dense Object Detector](https://mlsanity.com/paper/2008.13367/) (2020)
- [Oriented R-CNN for Object Detection](https://mlsanity.com/paper/2108.05699/) (2021)
- [R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object](https://mlsanity.com/paper/1908.05612/) (2019)
- [Align Deep Features for Oriented Object Detection](https://mlsanity.com/paper/2008.09397/) (2020)
- [OTA: Optimal Transport Assignment for Object Detection](https://mlsanity.com/paper/2103.14259/) (2021)
- [Acquisition of Localization Confidence for Accurate Object Detection](https://mlsanity.com/paper/1807.11590/) (2018)
- [Probabilistic Anchor Assignment with IoU Prediction for Object Detection](https://mlsanity.com/paper/2007.08103/) (2020)
- [Gliding vertex on the horizontal bounding box for multi-oriented object detection](https://mlsanity.com/paper/1911.09358/) (2019)
- [IoU Loss for 2D/3D Object Detection](https://mlsanity.com/paper/1908.03851/) (2019)
- [MMRotate: A Rotated Object Detection Benchmark using PyTorch](https://mlsanity.com/paper/2204.13317/) (2022)
- [Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection](https://mlsanity.com/paper/2011.12885/) (2020)
- [The KFIoU Loss for Rotated Object Detection](https://mlsanity.com/paper/2201.12558/) (2022)
- [AO2-DETR: Arbitrary-Oriented Object Detection Transformer](https://mlsanity.com/paper/2205.12785/) (2022)
- [Adaptive Rotated Convolution for Rotated Object Detection](https://mlsanity.com/paper/2303.07820/) (2023)
- [Rank-DETR for High Quality Object Detection](https://mlsanity.com/paper/2310.08854/) (2023)
- [Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection](https://mlsanity.com/paper/2304.08876/) (2023)
- [Rank & Sort Loss for Object Detection and Instance Segmentation](https://mlsanity.com/paper/2107.11669/) (2021)
- [Gaussian Bounding Boxes and Probabilistic Intersection-over-Union for Object Detection](https://mlsanity.com/paper/2106.06072/) (2021)
- [Correlation Loss: Enforcing Correlation between Classification and Localization](https://mlsanity.com/paper/2301.01019/) (2023)

## Abstract (arXiv)

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% AP50:95 on Rotated RetinaNet and +2.32% on STD).