# Exploiting Image Translations via Ensemble Self-Supervised Learning for Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/2107.06235 · HTML: https://mlsanity.com/paper/2107.06235/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 50 references that are in the map.
- First posted on arXiv 13 Jul 2021.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [Domain Separation Networks](https://mlsanity.com/paper/1608.06019/) (2016)
- [Bidirectional Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/1904.10620/) (2019)
- [Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation](https://mlsanity.com/paper/1809.09478/) (2018)
- [DLOW: Domain Flow for Adaptation and Generalization](https://mlsanity.com/paper/1812.05418/) (2018)
- [Image to Image Translation for Domain Adaptation](https://mlsanity.com/paper/1712.00479/) (2017)
- [Domain Adaptation for Structured Output via Discriminative Patch Representations](https://mlsanity.com/paper/1901.05427/) (2019)
- [All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation](https://mlsanity.com/paper/1903.12212/) (2019)
- [DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation](https://mlsanity.com/paper/1804.05827/) (2018)
- [Cluster Alignment with a Teacher for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.09980/) (2019)
- [A Deeper Look at Dataset Bias](https://mlsanity.com/paper/1505.01257/) (2015)
- [Fully Convolutional Adaptation Networks for Semantic Segmentation](https://mlsanity.com/paper/1804.08286/) (2018)
- [Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2003.04614/) (2020)
- [Phase Consistent Ecological Domain Adaptation](https://mlsanity.com/paper/2004.04923/) (2020)
- [Strong Baselines for Neural Semi-supervised Learning under Domain Shift](https://mlsanity.com/paper/1804.09530/) (2018)
- [Knowledge Distillation Methods for Efficient Unsupervised Adaptation Across Multiple Domains](https://mlsanity.com/paper/2101.07308/) (2021)
- [Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation](https://mlsanity.com/paper/1711.06969/) (2017)
- [A Domain Agnostic Normalization Layer for Unsupervised Adversarial Domain Adaptation](https://mlsanity.com/paper/1809.05298/) (2018)
- [A Fully Convolutional Tri-branch Network (FCTN) for Domain Adaptation](https://mlsanity.com/paper/1711.03694/) (2017)

## Built on by (most cited first, 6 of 6)

- [Exploring the Benefits of Vision Foundation Models for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2406.09896/) (2024)
- [Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation](https://mlsanity.com/paper/2302.06992/) (2023)
- [Training Semantic Segmentation on Heterogeneous Datasets](https://mlsanity.com/paper/2301.07634/) (2023)
- [Pre-Training Transformers for Domain Adaptation](https://mlsanity.com/paper/2112.09965/) (2021)
- [Divide, Ensemble and Conquer: The Last Mile on Unsupervised Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2406.18809/) (2024)
- [Layer-wise Model Merging for Unsupervised Domain Adaptation in Segmentation Tasks](https://mlsanity.com/paper/2409.15813/) (2024)

## Abstract (arXiv)

We introduce an unsupervised domain adaption (UDA) strategy that combines multiple image translations, ensemble learning and self-supervised learning in one coherent approach. We focus on one of the standard tasks of UDA in which a semantic segmentation model is trained on labeled synthetic data together with unlabeled real-world data, aiming to perform well on the latter. To exploit the advantage of using multiple image translations, we propose an ensemble learning approach, where three classifiers calculate their prediction by taking as input features of different image translations, making each classifier learn independently, with the purpose of combining their outputs by sparse Multinomial Logistic Regression. This regression layer known as meta-learner helps to reduce the bias during pseudo label generation when performing self-supervised learning and improves the generalizability of the model by taking into consideration the contribution of each classifier. We evaluate our method on the standard UDA benchmarks, i.e. adapting GTA V and Synthia to Cityscapes, and achieve state-of-the-art results in the mean intersection over union metric. Extensive ablation experiments are reported to highlight the advantageous properties of our proposed UDA strategy.