# Online Pseudo-Label Unified Object Detection for Multiple Datasets Training

arXiv: https://arxiv.org/abs/2410.15569 · HTML: https://mlsanity.com/paper/2410.15569/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 34 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## Builds on (most cited first, 29 of 29)

- [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)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring](https://mlsanity.com/paper/1911.09785/) (2019)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [WIDER FACE: A Face Detection Benchmark](https://mlsanity.com/paper/1511.06523/) (2015)
- [Simple multi-dataset detection](https://mlsanity.com/paper/2102.13086/) (2021)
- [Hierarchical Deep Stereo Matching on High-resolution Images](https://mlsanity.com/paper/1912.06704/) (2019)
- [MSeg: A Composite Dataset for Multi-domain Semantic Segmentation](https://mlsanity.com/paper/2112.13762/) (2021)
- [Towards Universal Object Detection by Domain Attention](https://mlsanity.com/paper/1904.04402/) (2019)
- [Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training](https://mlsanity.com/paper/2308.09718/) (2023)
- [Object Detection with a Unified Label Space from Multiple Datasets](https://mlsanity.com/paper/2008.06614/) (2020)
- [Detecting Everything in the Open World: Towards Universal Object Detection](https://mlsanity.com/paper/2303.11749/) (2023)
- [Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection](https://mlsanity.com/paper/2209.01589/) (2022)
- [Uni3D: A Unified Baseline for Multi-dataset 3D Object Detection](https://mlsanity.com/paper/2303.06880/) (2023)
- [BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training](https://mlsanity.com/paper/2203.13249/) (2022)
- [Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding](https://mlsanity.com/paper/2206.03484/) (2022)
- [Cascade-DETR: Delving into High-Quality Universal Object Detection](https://mlsanity.com/paper/2307.11035/) (2023)
- [Training of Convolutional Networks on Multiple Heterogeneous Datasets for Street Scene Semantic Segmentation](https://mlsanity.com/paper/1803.05675/) (2018)
- [Detecting Heads using Feature Refine Net and Cascaded Multi-Scale Architecture](https://mlsanity.com/paper/1803.09256/) (2018)
- [Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN](https://mlsanity.com/paper/2002.07417/) (2020)
- [ScaleDet: A Scalable Multi-Dataset Object Detector](https://mlsanity.com/paper/2306.04849/) (2023)
- [USB: Universal-Scale Object Detection Benchmark](https://mlsanity.com/paper/2103.14027/) (2021)
- [Universal Object Detection with Large Vision Model](https://mlsanity.com/paper/2212.09408/) (2022)
- [Non-iterative optimization of pseudo-labeling thresholds for training object detection models from multiple datasets](https://mlsanity.com/paper/2210.10221/) (2022)

## Abstract (arXiv)

The Unified Object Detection (UOD) task aims to achieve object detection of all merged categories through training on multiple datasets, and is of great significance in comprehensive object detection scenarios. In this paper, we conduct a thorough analysis of the cross datasets missing annotations issue, and propose an Online Pseudo-Label Unified Object Detection scheme. Our method uses a periodically updated teacher model to generate pseudo-labels for the unlabelled objects in each sub-dataset. This periodical update strategy could better ensure that the accuracy of the teacher model reaches the local maxima and maximized the quality of pseudo-labels. In addition, we survey the influence of overlapped region proposals on the accuracy of box regression. We propose a category specific box regression and a pseudo-label RPN head to improve the recall rate of the Region Proposal Network (PRN). Our experimental results on common used benchmarks (eg COCO, Object365 and OpenImages) indicates that our online pseudo-label UOD method achieves higher accuracy than existing SOTA methods.