# 3rd Place Solution for VisDA 2021 Challenge -- Universally Domain Adaptive Image Recognition

arXiv: https://arxiv.org/abs/2110.14240 · HTML: https://mlsanity.com/paper/2110.14240/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 11 references that are in the map.
- First posted on arXiv 27 Oct 2021.

## Builds on (most cited first, 9 of 9)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [VOLO: Vision Outlooker for Visual Recognition](https://mlsanity.com/paper/2106.13112/) (2021)
- [All Tokens Matter: Token Labeling for Training Better Vision Transformers](https://mlsanity.com/paper/2104.10858/) (2021)
- [OVANet: One-vs-All Network for Universal Domain Adaptation](https://mlsanity.com/paper/2104.03344/) (2021)

## Built on by (most cited first, 2 of 2)

- [Challenges for Monocular 6D Object Pose Estimation in Robotics](https://mlsanity.com/paper/2307.12172/) (2023)
- [Open Challenges for Monocular Single-shot 6D Object Pose Estimation](https://mlsanity.com/paper/2302.11827/) (2023)

## Abstract (arXiv)

The Visual Domain Adaptation (VisDA) 2021 Challenge calls for unsupervised domain adaptation (UDA) methods that can deal with both input distribution shift and label set variance between the source and target domains. In this report, we introduce a universal domain adaptation (UniDA) method by aggregating several popular feature extraction and domain adaptation schemes. First, we utilize VOLO, a Transformer-based architecture with state-of-the-art performance in several visual tasks, as the backbone to extract effective feature representations. Second, we modify the open-set classifier of OVANet to recognize the unknown class with competitive accuracy and robustness. As shown in the leaderboard, our proposed UniDA method ranks the 3rd place with 48.49% ACC and 70.8% AUROC in the VisDA 2021 Challenge.