# mDALU: Multi-Source Domain Adaptation and Label Unification with Partial Datasets

arXiv: https://arxiv.org/abs/2012.08385 · HTML: https://mlsanity.com/paper/2012.08385/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Dec 2020.

## Built on by (most cited first, 19 of 19)

- [All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenes](https://mlsanity.com/paper/2312.12176/) (2023)
- [Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation](https://mlsanity.com/paper/2101.07253/) (2021)
- [Uni3D: A Unified Baseline for Multi-dataset 3D Object Detection](https://mlsanity.com/paper/2303.06880/) (2023)
- [Transfer beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation](https://mlsanity.com/paper/2110.11062/) (2021)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey](https://mlsanity.com/paper/2112.03241/) (2021)
- [GM-DF: Generalized Multi-Scenario Deepfake Detection](https://mlsanity.com/paper/2406.20078/) (2024)
- [Bringing Generalization to Deep Multi-View Pedestrian Detection](https://mlsanity.com/paper/2109.12227/) (2021)
- [Learning with Style: Continual Semantic Segmentation Across Tasks and Domains](https://mlsanity.com/paper/2210.07016/) (2022)
- [More is Better: Deep Domain Adaptation with Multiple Sources](https://mlsanity.com/paper/2405.00749/) (2024)
- [DualCross: Cross-Modality Cross-Domain Adaptation for Monocular BEV Perception](https://mlsanity.com/paper/2305.03724/) (2023)
- [Universal Object Detection with Large Vision Model](https://mlsanity.com/paper/2212.09408/) (2022)
- [COLA: COarse LAbel pre-training for 3D semantic segmentation of sparse LiDAR datasets](https://mlsanity.com/paper/2202.06884/) (2022)
- [Uni2Det: Unified and Universal Framework for Prompt-Guided Multi-dataset 3D Detection](https://mlsanity.com/paper/2409.20558/) (2024)
- [Reiterative Domain Aware Multi-Target Adaptation](https://mlsanity.com/paper/2109.00919/) (2021)
- [Target Domain Data induces Negative Transfer in Mixed Domain Training with Disjoint Classes](https://mlsanity.com/paper/2303.01003/) (2023)
- [Unsupervised Federated Domain Adaptation for Segmentation of MRI Images](https://mlsanity.com/paper/2401.02941/) (2024)
- [Label Sharing Incremental Learning Framework for Independent Multi-Label Segmentation Tasks](https://mlsanity.com/paper/2411.11105/) (2024)
- [Seeking Universal Shot Language Understanding Solutions](https://mlsanity.com/paper/2603.18448/) (2026)

## Abstract (arXiv)

One challenge of object recognition is to generalize to new domains, to more classes and/or to new modalities. This necessitates methods to combine and reuse existing datasets that may belong to different domains, have partial annotations, and/or have different data modalities. This paper formulates this as a multi-source domain adaptation and label unification problem, and proposes a novel method for it. Our method consists of a partially-supervised adaptation stage and a fully-supervised adaptation stage. In the former, partial knowledge is transferred from multiple source domains to the target domain and fused therein. Negative transfer between unmatching label spaces is mitigated via three new modules: domain attention, uncertainty maximization and attention-guided adversarial alignment. In the latter, knowledge is transferred in the unified label space after a label completion process with pseudo-labels. Extensive experiments on three different tasks - image classification, 2D semantic image segmentation, and joint 2D-3D semantic segmentation - show that our method outperforms all competing methods significantly.