# Mutual Supervision for Dense Object Detection

Source: [Mutual Supervision for Dense Object Detection](<https://www.sota2.com/research/paper/68fa6ad21e209131cea2a909>)

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

Data updated: 2025-10-25T23:34:16.637Z

Authors: Ziteng Gao, Limin Wang, Gangshan Wu

Published: 2021-09-13T14:04:13.000Z

## Abstract

The classification and regression head are both indispensable components to build up a dense object detector, which are usually supervised by the same training samples and thus expected to have consistency with each other for detecting objects accurately in the detection pipeline. In this paper, we break the convention of the same training samples for these two heads in dense detectors and explore a novel supervisory paradigm, termed as Mutual Supervision (MuSu), to respectively and mutually assign training samples for the classification and regression head to ensure this consistency. MuSu defines training samples for the regression head mainly based on classification predicting scores and in turn, defines samples for the classification head based on localization scores from the regression head. Experimental results show that the convergence of detectors trained by this mutual supervision is guaranteed and the effectiveness of the proposed method is verified on the challenging MS COCO benchmark. We also find that tiling more anchors at the same location benefits detectors and leads to further improvements under this training scheme. We hope this work can inspire further researches on the interaction of the classification and regression task in detection and the supervision paradigm for detectors, especially separately for these two heads.

## 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 v2017 (test-dev)](<https://www.sota2.com/research/sota/object-detection-on-coco-v2017-test-dev.md>): Object Detection; COCO v2017 (test-dev); mAP: 47.4.

- [Object Detection on COCO 2017 (val)](<https://www.sota2.com/research/sota/object-detection-on-coco-2017-val.md>): Object Detection; COCO 2017 (val); AP: 40.6.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2109.05986>)

[PDF](<https://arxiv.org/pdf/2109.05986.pdf>)
