# Reiterative Domain Aware Multi-Target Adaptation

arXiv: https://arxiv.org/abs/2109.00919 · HTML: https://mlsanity.com/paper/2109.00919/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 39 of its 59 references that are in the map.
- First posted on arXiv 26 Aug 2021.

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Unsupervised Domain Adaptation with Residual Transfer Networks](https://mlsanity.com/paper/1602.04433/) (2016)
- [Bridging Theory and Algorithm for Domain Adaptation](https://mlsanity.com/paper/1904.05801/) (2019)
- [Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem](https://mlsanity.com/paper/1812.05720/) (2018)
- [Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks](https://mlsanity.com/paper/1612.05424/) (2016)
- [Escaping the Big Data Paradigm with Compact Transformers](https://mlsanity.com/paper/2104.05704/) (2021)
- [Automated Curriculum Learning for Neural Networks](https://mlsanity.com/paper/1704.03003/) (2017)
- [LocalViT: Analyzing Locality in Vision Transformers](https://mlsanity.com/paper/2104.05707/) (2021)
- [Open Set Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1804.10427/) (2018)
- [ViTGAN: Training GANs with Vision Transformers](https://mlsanity.com/paper/2107.04589/) (2021)
- [Incremental Learning Through Deep Adaptation](https://mlsanity.com/paper/1705.04228/) (2017)
- [Toward Transformer-Based Object Detection](https://mlsanity.com/paper/2012.09958/) (2020)
- [Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.11249/) (2021)
- [Unsupervised Multi-Target Domain Adaptation: An Information Theoretic Approach](https://mlsanity.com/paper/1810.11547/) (2018)
- [Progressive Graph Learning for Open-Set Domain Adaptation](https://mlsanity.com/paper/2006.12087/) (2020)
- [Incremental Adversarial Domain Adaptation for Continually Changing Environments](https://mlsanity.com/paper/1712.07436/) (2017)
- [Unsupervised Multi-Target Domain Adaptation Through Knowledge Distillation](https://mlsanity.com/paper/2007.07077/) (2020)

## Abstract (arXiv)

Most domain adaptation methods focus on single-source-single-target adaptation settings. Multi-target domain adaptation is a powerful extension in which a single classifier is learned for multiple unlabeled target domains. To build a multi-target classifier, it is important to have: a feature extractor that generalizes well across domains; and effective aggregation of features from the labeled source and different unlabeled target domains. Towards the first, we use the recently popular Transformer as a feature extraction backbone. Towards the second, we use a co-teaching-based approach using a dual-classifier head, one of which is based on the graph neural network. The proposed approach uses a sequential adaptation strategy that adapts one domain at a time starting from the target domains that are more similar to the source, assuming that the network finds it easier to adapt to such target domains. After adapting on each target, samples with a softmax-based confidence score greater than a threshold are added to the pseudo-source, thus aggregating knowledge from different domains. However, softmax is not entirely trustworthy as a confidence score and may generate a high score for unreliable samples if trained for many iterations. To mitigate this effect, we adopt a reiterative approach, where we reduce target adaptation iterations, however, reiterate multiple times over the target domains. The experimental evaluation on the Office-Home, Office-31 and DomainNet datasets shows significant improvement over the existing methods. We have achieved 10.7% average improvement in Office-Home dataset over the state-of-art methods.