# Gradient Harmonized Single-stage Detector

Source: [Gradient Harmonized Single-stage Detector](<https://www.sota2.com/research/paper/68fa65171e209131cea083bd>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-25T02:22:09.314Z

Authors: Buyu Li, Yu Liu, Xiaogang Wang

Published: 2018-11-13T09:47:52.000Z

## Abstract

Despite the great success of two-stage detectors, single-stage detector is still a more elegant and efficient way, yet suffers from the two well-known disharmonies during training, i.e. the huge difference in quantity between positive and negative examples as well as between easy and hard examples. In this work, we first point out that the essential effect of the two disharmonies can be summarized in term of the gradient. Further, we propose a novel gradient harmonizing mechanism (GHM) to be a hedging for the disharmonies. The philosophy behind GHM can be easily embedded into both classification loss function like cross-entropy (CE) and regression loss function like smooth-$L\_1$ ($SL\_1$) loss. To this end, two novel loss functions called GHM-C and GHM-R are designed to balancing the gradient flow for anchor classification and bounding box refinement, respectively. Ablation study on MS COCO demonstrates that without laborious hyper-parameter tuning, both GHM-C and GHM-R can bring substantial improvement for single-stage detector. Without any whistles and bells, our model achieves 41.6 mAP on COCO test-dev set which surpasses the state-of-the-art method, Focal Loss (FL) + $SL\_1$, by 0.8.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Object Detection on COCO (test-dev)](<https://www.sota2.com/research/sota/object-detection-on-coco-test-dev.md>): Object Detection; COCO (test-dev); mAP: 41.6.

- [Object Detection on MS-COCO 2017 (val)](<https://www.sota2.com/research/sota/object-detection-on-ms-coco-2017-val.md>): Object Detection; MS-COCO 2017 (val); mAP: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1811.05181>)

[PDF](<https://arxiv.org/pdf/1811.05181.pdf>)

[Implementation](<https://github.com/libuyu/GHM_Detection>)