# Beyond the Known: Enhancing Open Set Domain Adaptation with Unknown Exploration

arXiv: https://arxiv.org/abs/2412.18105 · HTML: https://mlsanity.com/paper/2412.18105/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 31 references that are in the map.
- First posted on arXiv 24 Dec 2024.

## Builds on (most cited first, 17 of 17)

- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Open-Set Recognition: a Good Closed-Set Classifier is All You Need?](https://mlsanity.com/paper/2110.06207/) (2021)
- [Recent Advances in Open Set Recognition: A Survey](https://mlsanity.com/paper/1811.08581/) (2018)
- [Universal Domain Adaptation through Self Supervision](https://mlsanity.com/paper/2002.07953/) (2020)
- [Adversarial Reciprocal Points Learning for Open Set Recognition](https://mlsanity.com/paper/2103.00953/) (2021)
- [Open Set Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1804.10427/) (2018)
- [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)
- [MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation](https://mlsanity.com/paper/2312.07871/) (2023)
- [Just DIAL: DomaIn Alignment Layers for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1702.06332/) (2017)
- [Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptation](https://mlsanity.com/paper/2107.02067/) (2021)
- [Improving Transferability of Domain Adaptation Networks Through Domain Alignment Layers](https://mlsanity.com/paper/2109.02693/) (2021)
- [Low-Budget Label Query through Domain Alignment Enforcement](https://mlsanity.com/paper/2001.00238/) (2020)
- [Open Set Domain Adaptation by Extreme Value Theory](https://mlsanity.com/paper/2101.02561/) (2020)
- [Tightening Classification Boundaries in Open Set Domain Adaptation through Unknown Exploitation](https://mlsanity.com/paper/2309.08964/) (2023)

## Built on by (most cited first, 1 of 1)

- [E-MLNet: Enhanced Mutual Learning for Universal Domain Adaptation with Sample-Specific Weighting](https://mlsanity.com/paper/2509.09006/) (2025)

## Abstract (arXiv)

Convolutional neural networks (CNNs) can learn directly from raw data, resulting in exceptional performance across various research areas. However, factors present in non-controllable environments such as unlabeled datasets with varying levels of domain and category shift can reduce model accuracy. The Open Set Domain Adaptation (OSDA) is a challenging problem that arises when both of these issues occur together. Existing OSDA approaches in literature only align known classes or use supervised training to learn unknown classes as a single new category. In this work, we introduce a new approach to improve OSDA techniques by extracting a set of high-confidence unknown instances and using it as a hard constraint to tighten the classification boundaries. Specifically, we use a new loss constraint that is evaluated in three different ways: (1) using pristine negative instances directly; (2) using data augmentation techniques to create randomly transformed negatives; and (3) with generated synthetic negatives containing adversarial features. We analyze different strategies to improve the discriminator and the training of the Generative Adversarial Network (GAN) used to generate synthetic negatives. We conducted extensive experiments and analysis on OVANet using three widely-used public benchmarks, the Office-31, Office-Home, and VisDA datasets. We were able to achieve similar H-score to other state-of-the-art methods, while increasing the accuracy on unknown categories.