Papers › HQOD: Harmonious Quantization for Object Detection

HQOD: Harmonious Quantization for Object Detection

5 Aug 2024arXiv:2408.02561archive 2025-07-28

Long Huang, Zhiwei Dong, Song-Lu Chen, Ruiyao Zhang, Shutong Ti, Feng Chen, Xu-Cheng Yin

Task inharmony problem commonly occurs in modern object detectors, leading to inconsistent qualities between classification and regression tasks. The predicted boxes with high classification scores but poor localization positions or low classification scores but accurate localization positions will worsen the performance of detectors after Non-Maximum Suppression. Furthermore, when object detectors collaborate with Quantization-Aware Training (QAT), we observe that the task inharmony problem will be further exacerbated, which is considered one of the main causes of the performance degradation of quantized detectors. To tackle this issue, we propose the Harmonious Quantization for Object Detection (HQOD) framework, which consists of two components. Firstly, we propose a task-correlated loss to encourage detectors to focus on improving samples with lower task harmony quality during QAT. Secondly, a harmonious Intersection over Union (IoU) loss is incorporated to balance the optimization of the regression branch across different IoU levels. The proposed HQOD can be easily integrated into different QAT algorithms and detectors. Remarkably, on the MS COCO dataset, our 4-bit ATSS with ResNet-50 backbone achieves a state-of-the-art mAP of 39.6%, even surpassing the full-precision one.

PaperPDFCode

Code

Menace-Dragon/VP-QOD officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ObjectObject DetectionQuantizationobject-detectionregression

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ATSSFocus

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections