# Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/2007.07695 · HTML: https://mlsanity.com/paper/2007.07695/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2020.

## Built on by (most cited first, 30 of 35)

- [ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection](https://mlsanity.com/paper/2103.05346/) (2021)
- [Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation](https://mlsanity.com/paper/2205.04183/) (2022)
- [Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networks](https://mlsanity.com/paper/2207.05444/) (2022)
- [Safe Self-Refinement for Transformer-based Domain Adaptation](https://mlsanity.com/paper/2204.07683/) (2022)
- [ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection](https://mlsanity.com/paper/2108.06682/) (2021)
- [Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing](https://mlsanity.com/paper/2110.15128/) (2021)
- [Compound Domain Generalization via Meta-Knowledge Encoding](https://mlsanity.com/paper/2203.13006/) (2022)
- [Transporting Causal Mechanisms for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2107.11055/) (2021)
- [Coarse-to-Fine Domain Adaptive Semantic Segmentation with Photometric Alignment and Category-Center Regularization](https://mlsanity.com/paper/2103.13041/) (2021)
- [A Survey of Unsupervised Domain Adaptation for Visual Recognition](https://mlsanity.com/paper/2112.06745/) (2021)
- [LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models](https://mlsanity.com/paper/2407.08966/) (2024)
- [Localized Adversarial Domain Generalization](https://mlsanity.com/paper/2205.04114/) (2022)
- [Transferrable Contrastive Learning for Visual Domain Adaptation](https://mlsanity.com/paper/2112.07516/) (2021)
- [Which Pixel to Annotate: a Label-Efficient Nuclei Segmentation Framework](https://mlsanity.com/paper/2212.10305/) (2022)
- [Towards Novel Target Discovery Through Open-Set Domain Adaptation](https://mlsanity.com/paper/2105.02432/) (2021)
- [Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners](https://mlsanity.com/paper/2106.00417/) (2021)
- [Gradual Domain Adaptation via Self-Training of Auxiliary Models](https://mlsanity.com/paper/2106.09890/) (2021)
- [Improving Pseudo Labels With Intra-Class Similarity for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2207.12139/) (2022)
- [CycDA: Unsupervised Cycle Domain Adaptation from Image to Video](https://mlsanity.com/paper/2203.16244/) (2022)
- [Learning by Hallucinating: Vision-Language Pre-training with Weak Supervision](https://mlsanity.com/paper/2210.13591/) (2022)
- [Semi-supervised Deep Multi-view Stereo](https://mlsanity.com/paper/2207.11699/) (2022)
- [ConDA: Continual Unsupervised Domain Adaptation](https://mlsanity.com/paper/2103.11056/) (2021)
- [On Universal Black-Box Domain Adaptation](https://mlsanity.com/paper/2104.04665/) (2021)
- [Domain Adaptation and Generalization on Functional Medical Images: A Systematic Survey](https://mlsanity.com/paper/2212.03176/) (2022)
- [Reciprocal Normalization for Domain Adaptation](https://mlsanity.com/paper/2112.10474/) (2021)
- [More Than Meets The Eye: Semi-supervised Learning Under Non-IID Data](https://mlsanity.com/paper/2104.10223/) (2021)
- [Towards Category and Domain Alignment: Category-Invariant Feature Enhancement for Adversarial Domain Adaptation](https://mlsanity.com/paper/2108.06583/) (2021)
- [MetaPix: Domain Transfer for Semantic Segmentation by Meta Pixel Weighting](https://mlsanity.com/paper/2110.01777/) (2021)
- [CA-UDA: Class-Aware Unsupervised Domain Adaptation with Optimal Assignment and Pseudo-Label Refinement](https://mlsanity.com/paper/2205.13579/) (2022)
- [Subtype-Aware Dynamic Unsupervised Domain Adaptation](https://mlsanity.com/paper/2208.07754/) (2022)

## Abstract (arXiv)

Motivated by the problem relatedness between unsupervised domain adaptation (UDA) and semi-supervised learning (SSL), many state-of-the-art UDA methods adopt SSL principles (e.g., the cluster assumption) as their learning ingredients. However, they tend to overlook the very domain-shift nature of UDA. In this work, we take a step further to study the proper extensions of SSL techniques for UDA. Taking the algorithm of label propagation (LP) as an example, we analyze the challenges of adopting LP to UDA and theoretically analyze the conditions of affinity graph/matrix construction in order to achieve better propagation of true labels to unlabeled instances. Our analysis suggests a new algorithm of Label Propagation with Augmented Anchors (A2LP), which could potentially improve LP via generation of unlabeled virtual instances (i.e., the augmented anchors) with high-confidence label predictions. To make the proposed A2LP useful for UDA, we propose empirical schemes to generate such virtual instances. The proposed schemes also tackle the domain-shift challenge of UDA by alternating between pseudo labeling via A2LP and domain-invariant feature learning. Experiments show that such a simple SSL extension improves over representative UDA methods of domain-invariant feature learning, and could empower two state-of-the-art methods on benchmark UDA datasets. Our results show the value of further investigation on SSL techniques for UDA problems.