# Dynamic Supervisor for Cross-dataset Object Detection

arXiv: https://arxiv.org/abs/2204.00183 · HTML: https://mlsanity.com/paper/2204.00183/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 38 references that are in the map.
- First posted on arXiv 1 Apr 2022.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Does label smoothing mitigate label noise?](https://mlsanity.com/paper/2003.02819/) (2020)
- [Data Distillation: Towards Omni-Supervised Learning](https://mlsanity.com/paper/1712.04440/) (2017)
- [PCL: Proposal Cluster Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1807.03342/) (2018)
- [Towards Universal Object Detection by Domain Attention](https://mlsanity.com/paper/1904.04402/) (2019)
- [Object Detection with a Unified Label Space from Multiple Datasets](https://mlsanity.com/paper/2008.06614/) (2020)
- [NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detection](https://mlsanity.com/paper/1812.00124/) (2018)
- [Soft Sampling for Robust Object Detection](https://mlsanity.com/paper/1806.06986/) (2018)
- [Training Object Detectors With Noisy Data](https://mlsanity.com/paper/1905.07202/) (2019)
- [Object Detection as a Positive-Unlabeled Problem](https://mlsanity.com/paper/2002.04672/) (2020)
- [Cost-effective Object Detection: Active Sample Mining with Switchable Selection Criteria](https://mlsanity.com/paper/1807.00147/) (2018)
- [OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation](https://mlsanity.com/paper/1812.02611/) (2018)
- [Self-supervised Robust Object Detectors from Partially Labelled Datasets](https://mlsanity.com/paper/2005.11549/) (2020)

## Built on by (most cited first, 1 of 1)

- [Improving Layout Representation Learning Across Inconsistently Annotated Datasets via Agentic Harmonization](https://mlsanity.com/paper/2604.11042/) (2026)

## Abstract (arXiv)

The application of cross-dataset training in object detection tasks is complicated because the inconsistency in the category range across datasets transforms fully supervised learning into semi-supervised learning. To address this problem, recent studies focus on the generation of high-quality missing annotations. In this study, we first point out that it is not enough to generate high-quality annotations using a single model, which only looks once for annotations. Through detailed experimental analyses, we further conclude that hard-label training is conducive to generating high-recall annotations, while soft-label training tends to obtain high-precision annotations. Inspired by the aspects mentioned above, we propose a dynamic supervisor framework that updates the annotations multiple times through multiple-updated submodels trained using hard and soft labels. In the final generated annotations, both recall and precision improve significantly through the integration of hard-label training with soft-label training. Extensive experiments conducted on various dataset combination settings support our analyses and demonstrate the superior performance of the proposed dynamic supervisor.