# Towards Adaptive Unknown Authentication for Universal Domain Adaptation by Classifier Paradox

arXiv: https://arxiv.org/abs/2207.04494 · HTML: https://mlsanity.com/paper/2207.04494/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 10 Jul 2022.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Semi-supervised Domain Adaptation via Minimax Entropy](https://mlsanity.com/paper/1904.06487/) (2019)
- [Domain Separation Networks](https://mlsanity.com/paper/1608.06019/) (2016)
- [Universal Domain Adaptation through Self Supervision](https://mlsanity.com/paper/2002.07953/) (2020)
- [ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection](https://mlsanity.com/paper/2103.05346/) (2021)
- [Open Set Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1804.10427/) (2018)
- [Partial Adversarial Domain Adaptation](https://mlsanity.com/paper/1808.04205/) (2018)
- [L2-constrained Softmax Loss for Discriminative Face Verification](https://mlsanity.com/paper/1703.09507/) (2017)
- [OVANet: One-vs-All Network for Universal Domain Adaptation](https://mlsanity.com/paper/2104.03344/) (2021)
- [On the Effectiveness of Image Rotation for Open Set Domain Adaptation](https://mlsanity.com/paper/2007.12360/) (2020)
- [Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1908.00262/) (2019)
- [Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networks](https://mlsanity.com/paper/2007.05134/) (2020)
- [Exploring Category-Agnostic Clusters for Open-Set Domain Adaptation](https://mlsanity.com/paper/2006.06567/) (2020)
- [UMAD: Universal Model Adaptation under Domain and Category Shift](https://mlsanity.com/paper/2112.08553/) (2021)
- [Divergence Optimization for Noisy Universal Domain Adaptation](https://mlsanity.com/paper/2104.00246/) (2021)

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

- [Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All-in-One Classifier](https://mlsanity.com/paper/2211.11262/) (2022)
- [Joint Distribution Alignment for Universal Domain Adaptation](https://mlsanity.com/paper/2608.24429/) (2026)

## Abstract (arXiv)

Universal domain adaptation (UniDA) is a general unsupervised domain adaptation setting, which addresses both domain and label shifts in adaptation. Its main challenge lies in how to identify target samples in unshared or unknown classes. Previous methods commonly strive to depict sample "confidence" along with a threshold for rejecting unknowns, and align feature distributions of shared classes across domains. However, it is still hard to pre-specify a "confidence" criterion and threshold which are adaptive to various real tasks, and a mis-prediction of unknowns further incurs misalignment of features in shared classes. In this paper, we propose a new UniDA method with adaptive Unknown Authentication by Classifier Paradox (UACP), considering that samples with paradoxical predictions are probably unknowns belonging to none of the source classes. In UACP, a composite classifier is jointly designed with two types of predictors. That is, a multi-class (MC) predictor classifies samples to one of the multiple source classes, while a binary one-vs-all (OVA) predictor further verifies the prediction by MC predictor. Samples with verification failure or paradox are identified as unknowns. Further, instead of feature alignment for shared classes, implicit domain alignment is conducted in output space such that samples across domains share the same decision boundary, though with feature discrepancy. Empirical results validate UACP under both open-set and universal UDA settings.