# Two-phase Pseudo Label Densification for Self-training based Domain Adaptation

arXiv: https://arxiv.org/abs/2012.04828 · HTML: https://mlsanity.com/paper/2012.04828/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Dec 2020.

## Built on by (most cited first, 30 of 60)

- [EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization](https://mlsanity.com/paper/2303.01904/) (2023)
- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.11249/) (2021)
- [Context-Aware Mixup for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.03557/) (2021)
- [MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2204.12667/) (2022)
- [Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.12940/) (2021)
- [Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation](https://mlsanity.com/paper/2303.14360/) (2023)
- [A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction](https://mlsanity.com/paper/2207.01223/) (2022)
- [Cross-View Regularization for Domain Adaptive Panoptic Segmentation](https://mlsanity.com/paper/2103.02584/) (2021)
- [Domain Adaptation for Underwater Image Enhancement](https://mlsanity.com/paper/2108.09650/) (2021)
- [GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation](https://mlsanity.com/paper/2207.09763/) (2022)
- [LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.05570/) (2021)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Dual Path Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/2108.06337/) (2021)
- [Leveraging Self-Supervision for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2103.16291/) (2021)
- [Dirichlet-based Uncertainty Calibration for Active Domain Adaptation](https://mlsanity.com/paper/2302.13824/) (2023)
- [DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2207.09988/) (2022)
- [CoNMix for Source-free Single and Multi-target Domain Adaptation](https://mlsanity.com/paper/2211.03876/) (2022)
- [Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2105.10843/) (2021)
- [Generative Self-training for Cross-domain Unsupervised Tagged-to-Cine MRI Synthesis](https://mlsanity.com/paper/2106.12499/) (2021)
- [Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey](https://mlsanity.com/paper/2112.03241/) (2021)
- [Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors](https://mlsanity.com/paper/2205.14467/) (2022)
- [Domain-Agnostic Prior for Transfer Semantic Segmentation](https://mlsanity.com/paper/2204.02684/) (2022)
- [Hyperbolic Active Learning for Semantic Segmentation under Domain Shift](https://mlsanity.com/paper/2306.11180/) (2023)
- [Unsupervised Domain Adaptive Salient Object Detection Through Uncertainty-Aware Pseudo-Label Learning](https://mlsanity.com/paper/2202.13170/) (2022)
- [Contrastive Vicinal Space for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2111.13353/) (2021)
- [Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2207.10892/) (2022)
- [Multiple Fusion Adaptation: A Strong Framework for Unsupervised Semantic Segmentation Adaptation](https://mlsanity.com/paper/2112.00295/) (2021)
- [Self-Distillation for Unsupervised 3D Domain Adaptation](https://mlsanity.com/paper/2210.08226/) (2022)
- [Make the U in UDA Matter: Invariant Consistency Learning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2309.12742/) (2023)

## Abstract (arXiv)

Recently, deep self-training approaches emerged as a powerful solution to the unsupervised domain adaptation. The self-training scheme involves iterative processing of target data; it generates target pseudo labels and retrains the network. However, since only the confident predictions are taken as pseudo labels, existing self-training approaches inevitably produce sparse pseudo labels in practice. We see this is critical because the resulting insufficient training-signals lead to a suboptimal, error-prone model. In order to tackle this problem, we propose a novel Two-phase Pseudo Label Densification framework, referred to as TPLD. In the first phase, we use sliding window voting to propagate the confident predictions, utilizing intrinsic spatial-correlations in the images. In the second phase, we perform a confidence-based easy-hard classification. For the easy samples, we now employ their full pseudo labels. For the hard ones, we instead adopt adversarial learning to enforce hard-to-easy feature alignment. To ease the training process and avoid noisy predictions, we introduce the bootstrapping mechanism to the original self-training loss. We show the proposed TPLD can be easily integrated into existing self-training based approaches and improves the performance significantly. Combined with the recently proposed CRST self-training framework, we achieve new state-of-the-art results on two standard UDA benchmarks.