# A Multi-stage Framework with Mean Subspace Computation and Recursive Feedback for Online Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/2207.00003 · HTML: https://mlsanity.com/paper/2207.00003/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 47 references that are in the map.
- First posted on arXiv 24 Jun 2022.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [Understanding Self-Training for Gradual Domain Adaptation](https://mlsanity.com/paper/2002.11361/) (2020)
- [Visual Domain Adaptation with Manifold Embedded Distribution Alignment](https://mlsanity.com/paper/1807.07258/) (2018)
- [Incremental Adversarial Domain Adaptation for Continually Changing Environments](https://mlsanity.com/paper/1712.07436/) (2017)
- [ACE: Adapting to Changing Environments for Semantic Segmentation](https://mlsanity.com/paper/1904.06268/) (2019)
- [Online Adaptation to Label Distribution Shift](https://mlsanity.com/paper/2107.04520/) (2021)
- [Joint Geometrical and Statistical Alignment for Visual Domain Adaptation](https://mlsanity.com/paper/1705.05498/) (2017)
- [Kitting in the Wild through Online Domain Adaptation](https://mlsanity.com/paper/1807.01028/) (2018)
- [Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation](https://mlsanity.com/paper/1703.01461/) (2017)
- [Multi-step Online Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08930/) (2020)
- [Online Domain Adaptation for Multi-Object Tracking](https://mlsanity.com/paper/1508.00776/) (2015)
- [Unsupervised Domain Adaptation using Graph Transduction Games](https://mlsanity.com/paper/1905.02036/) (2019)

## Built on by (most cited first, 3 of 3)

- [Uncertainty-Induced Transferability Representation for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2208.13986/) (2022)
- [Semantic-aware Message Broadcasting for Efficient Unsupervised Domain Adaptation](https://mlsanity.com/paper/2212.02739/) (2022)
- [Real-Time Online Unsupervised Domain Adaptation for Real-World Person Re-identification](https://mlsanity.com/paper/2306.03993/) (2023)

## Abstract (arXiv)

In this paper, we address the Online Unsupervised Domain Adaptation (OUDA) problem and propose a novel multi-stage framework to solve real-world situations when the target data are unlabeled and arriving online sequentially in batches. To project the data from the source and the target domains to a common subspace and manipulate the projected data in real-time, our proposed framework institutes a novel method, called an Incremental Computation of Mean-Subspace (ICMS) technique, which computes an approximation of mean-target subspace on a Grassmann manifold and is proven to be a close approximate to the Karcher mean. Furthermore, the transformation matrix computed from the mean-target subspace is applied to the next target data in the recursive-feedback stage, aligning the target data closer to the source domain. The computation of transformation matrix and the prediction of next-target subspace leverage the performance of the recursive-feedback stage by considering the cumulative temporal dependency among the flow of the target subspace on the Grassmann manifold. The labels of the transformed target data are predicted by the pre-trained source classifier, then the classifier is updated by the transformed data and predicted labels. Extensive experiments on six datasets were conducted to investigate in depth the effect and contribution of each stage in our proposed framework and its performance over previous approaches in terms of classification accuracy and computational speed. In addition, the experiments on traditional manifold-based learning models and neural-network-based learning models demonstrated the applicability of our proposed framework for various types of learning models.