# Subsidiary Prototype Alignment for Universal Domain Adaptation

arXiv: https://arxiv.org/abs/2210.15909 · HTML: https://mlsanity.com/paper/2210.15909/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 61 references that are in the map.
- First posted on arXiv 28 Oct 2022.

## Builds on (most cited first, 30 of 45)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [Domain Generalization by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1903.06864/) (2019)
- [Unsupervised Domain Adaptation with Residual Transfer Networks](https://mlsanity.com/paper/1602.04433/) (2016)
- [Do Adversarially Robust ImageNet Models Transfer Better?](https://mlsanity.com/paper/2007.08489/) (2020)
- [Characterizing and Avoiding Negative Transfer](https://mlsanity.com/paper/1811.09751/) (2018)
- [Universal Source-Free Domain Adaptation](https://mlsanity.com/paper/2004.04393/) (2020)
- [Colorization as a Proxy Task for Visual Understanding](https://mlsanity.com/paper/1703.04044/) (2017)
- [Universal Domain Adaptation through Self Supervision](https://mlsanity.com/paper/2002.07953/) (2020)
- [Open Set Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1804.10427/) (2018)
- [Classification-Reconstruction Learning for Open-Set Recognition](https://mlsanity.com/paper/1812.04246/) (2018)
- [C2AE: Class Conditioned Auto-Encoder for Open-set Recognition](https://mlsanity.com/paper/1904.01198/) (2019)
- [Partial Adversarial Domain Adaptation](https://mlsanity.com/paper/1808.04205/) (2018)
- [Unsupervised Domain Adaptation through Self-Supervision](https://mlsanity.com/paper/1909.11825/) (2019)
- [No More Discrimination: Cross City Adaptation of Road Scene Segmenters](https://mlsanity.com/paper/1704.08509/) (2017)
- [OVANet: One-vs-All Network for Universal Domain Adaptation](https://mlsanity.com/paper/2104.03344/) (2021)
- [Importance Weighted Adversarial Nets for Partial Domain Adaptation](https://mlsanity.com/paper/1803.09210/) (2018)
- [Learning to Transfer Examples for Partial Domain Adaptation](https://mlsanity.com/paper/1903.12230/) (2019)
- [A Closer Look at Smoothness in Domain Adversarial Training](https://mlsanity.com/paper/2206.08213/) (2022)
- [Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.11249/) (2021)

## Built on by (most cited first, 17 of 17)

- [Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection](https://mlsanity.com/paper/2306.09158/) (2023)
- [SPA: A Graph Spectral Alignment Perspective for Domain Adaptation](https://mlsanity.com/paper/2310.17594/) (2023)
- [Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All-in-One Classifier](https://mlsanity.com/paper/2211.11262/) (2022)
- [GeoNet: Benchmarking Unsupervised Adaptation across Geographies](https://mlsanity.com/paper/2303.15443/) (2023)
- [Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation](https://mlsanity.com/paper/2308.14023/) (2023)
- [Universal Domain Adaptation via Compressive Attention Matching](https://mlsanity.com/paper/2304.11862/) (2023)
- [Memory-Assisted Sub-Prototype Mining for Universal Domain Adaptation](https://mlsanity.com/paper/2310.05453/) (2023)
- [Learning Transferable Conceptual Prototypes for Interpretable Unsupervised Domain Adaptation](https://mlsanity.com/paper/2310.08071/) (2023)
- [COCA: Classifier-Oriented Calibration via Textual Prototype for Source-Free Universal Domain Adaptation](https://mlsanity.com/paper/2308.10450/) (2023)
- [Universal Domain Adaptation for Robust Handling of Distributional Shifts in NLP](https://mlsanity.com/paper/2310.14849/) (2023)
- [SPA++: Generalized Graph Spectral Alignment for Versatile Domain Adaptation](https://mlsanity.com/paper/2508.05182/) (2025)
- [Quantitative Estimation of Target Task Performance from Unsupervised Pretext Task in Semi/Self-Supervised Learning](https://mlsanity.com/paper/2508.07299/) (2025)
- [Tackling Dimensional Collapse toward Comprehensive Universal Domain Adaptation](https://mlsanity.com/paper/2410.11271/) (2024)
- [Prototypical Progressive Alignment and Reweighting for Generalizable Semantic Segmentation](https://mlsanity.com/paper/2507.11955/) (2025)
- [Joint Identifiability of Cross-Domain Recommendation via Hierarchical Subspace Disentanglement](https://mlsanity.com/paper/2404.04481/) (2024)
- [Uncertainty-guided Open-Set Source-Free Unsupervised Domain Adaptation with Target-private Class Segregation](https://mlsanity.com/paper/2404.10574/) (2024)
- [Adversarial Reweighting with α-Power Maximization for Domain Adaptation](https://mlsanity.com/paper/2404.17275/) (2024)

## Abstract (arXiv)

Universal Domain Adaptation (UniDA) deals with the problem of knowledge transfer between two datasets with domain-shift as well as category-shift. The goal is to categorize unlabeled target samples, either into one of the "known" categories or into a single "unknown" category. A major problem in UniDA is negative transfer, i.e. misalignment of "known" and "unknown" classes. To this end, we first uncover an intriguing tradeoff between negative-transfer-risk and domain-invariance exhibited at different layers of a deep network. It turns out we can strike a balance between these two metrics at a mid-level layer. Towards designing an effective framework based on this insight, we draw motivation from Bag-of-visual-Words (BoW). Word-prototypes in a BoW-like representation of a mid-level layer would represent lower-level visual primitives that are likely to be unaffected by the category-shift in the high-level features. We develop modifications that encourage learning of word-prototypes followed by word-histogram based classification. Following this, subsidiary prototype-space alignment (SPA) can be seen as a closed-set alignment problem, thereby avoiding negative transfer. We realize this with a novel word-histogram-related pretext task to enable closed-set SPA, operating in conjunction with goal task UniDA. We demonstrate the efficacy of our approach on top of existing UniDA techniques, yielding state-of-the-art performance across three standard UniDA and Open-Set DA object recognition benchmarks.