# UMAD: Universal Model Adaptation under Domain and Category Shift

arXiv: https://arxiv.org/abs/2112.08553 · HTML: https://mlsanity.com/paper/2112.08553/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 72 references that are in the map.
- First posted on arXiv 16 Dec 2021.

## Builds on (most cited first, 30 of 46)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [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)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [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)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges](https://mlsanity.com/paper/1902.07830/) (2019)
- [Universal Source-Free Domain Adaptation](https://mlsanity.com/paper/2004.04393/) (2020)
- [Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer](https://mlsanity.com/paper/2012.07297/) (2020)
- [Universal Domain Adaptation through Self Supervision](https://mlsanity.com/paper/2002.07953/) (2020)
- [Reducing Network Agnostophobia](https://mlsanity.com/paper/1811.04110/) (2018)
- [Asymmetric Tri-training for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1702.08400/) (2017)
- [Open Set Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1804.10427/) (2018)

## Built on by (most cited first, 23 of 23)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [Upcycling Models under Domain and Category Shift](https://mlsanity.com/paper/2303.07110/) (2023)
- [LEAD: Learning Decomposition for Source-free Universal Domain Adaptation](https://mlsanity.com/paper/2403.03421/) (2024)
- [MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation](https://mlsanity.com/paper/2312.07871/) (2023)
- [Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization](https://mlsanity.com/paper/2308.12919/) (2023)
- [Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2411.16064/) (2024)
- [Few-shot Fine-tuning is All You Need for Source-free Domain Adaptation](https://mlsanity.com/paper/2304.00792/) (2023)
- [Memory-Assisted Sub-Prototype Mining for Universal Domain Adaptation](https://mlsanity.com/paper/2310.05453/) (2023)
- [Recall and Refine: A Simple but Effective Source-free Open-set Domain Adaptation Framework](https://mlsanity.com/paper/2411.12558/) (2024)
- [GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning](https://mlsanity.com/paper/2403.14410/) (2024)
- [Memory-Efficient Pseudo-Labeling for Online Source-Free Universal Domain Adaptation using a Gaussian Mixture Model](https://mlsanity.com/paper/2407.14208/) (2024)
- [OneRing: A Simple Method for Source-free Open-partial Domain Adaptation](https://mlsanity.com/paper/2206.03600/) (2022)
- [COCA: Classifier-Oriented Calibration via Textual Prototype for Source-Free Universal Domain Adaptation](https://mlsanity.com/paper/2308.10450/) (2023)
- [Towards Adaptive Unknown Authentication for Universal Domain Adaptation by Classifier Paradox](https://mlsanity.com/paper/2207.04494/) (2022)
- [COMET: Contrastive Mean Teacher for Online Source-Free Universal Domain Adaptation](https://mlsanity.com/paper/2401.17728/) (2024)
- [Source-free Domain Adaptation Requires Penalized Diversity](https://mlsanity.com/paper/2304.02798/) (2023)
- [Adversarial Reweighting with α-Power Maximization for Domain Adaptation](https://mlsanity.com/paper/2404.17275/) (2024)
- [Analysis of Pseudo-Labeling for Online Source-Free Universal Domain Adaptation](https://mlsanity.com/paper/2504.11992/) (2025)
- [Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptation](https://mlsanity.com/paper/2510.00478/) (2025)
- [LFM: Leveraging Foundation Models for Source-Free Universal Domain Adaptation](https://mlsanity.com/paper/2607.17653/) (2026)
- [Reliable Neural Collapse Approximation for Open-World Test-Time Adaptation](https://mlsanity.com/paper/2608.19890/) (2026)
- [A Comprehensive Benchmark of Source-Free Universal Domain Adaptation on Time Series Representations](https://mlsanity.com/paper/2609.39810/) (2026)

## Abstract (arXiv)

Learning to reject unknown samples (not present in the source classes) in the target domain is fairly important for unsupervised domain adaptation (UDA). There exist two typical UDA scenarios, i.e., open-set, and open-partial-set, and the latter assumes that not all source classes appear in the target domain. However, most prior methods are designed for one UDA scenario and always perform badly on the other UDA scenario. Moreover, they also require the labeled source data during adaptation, limiting their usability in data privacy-sensitive applications. To address these issues, this paper proposes a Universal Model ADaptation (UMAD) framework which handles both UDA scenarios without access to the source data nor prior knowledge about the category shift between domains. Specifically, we aim to learn a source model with an elegantly designed two-head classifier and provide it to the target domain. During adaptation, we develop an informative consistency score to help distinguish unknown samples from known samples. To achieve bilateral adaptation in the target domain, we further maximize localized mutual information to align known samples with the source classifier and employ an entropic loss to push unknown samples far away from the source classification boundary, respectively. Experiments on open-set and open-partial-set UDA scenarios demonstrate that UMAD, as a unified approach without access to source data, exhibits comparable, if not superior, performance to state-of-the-art data-dependent methods.