# Exploring Category-Agnostic Clusters for Open-Set Domain Adaptation

arXiv: https://arxiv.org/abs/2006.06567 · HTML: https://mlsanity.com/paper/2006.06567/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2020.

## Built on by (most cited first, 27 of 27)

- [Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation](https://mlsanity.com/paper/2110.04202/) (2021)
- [Parametric Information Maximization for Generalized Category Discovery](https://mlsanity.com/paper/2212.00334/) (2022)
- [A Style and Semantic Memory Mechanism for Domain Generalization](https://mlsanity.com/paper/2112.07517/) (2021)
- [Source-Free Progressive Graph Learning for Open-Set Domain Adaptation](https://mlsanity.com/paper/2202.06174/) (2022)
- [Relation Matters: Foreground-aware Graph-based Relational Reasoning for Domain Adaptive Object Detection](https://mlsanity.com/paper/2206.02355/) (2022)
- [Subsidiary Prototype Alignment for Universal Domain Adaptation](https://mlsanity.com/paper/2210.15909/) (2022)
- [Transferrable Contrastive Learning for Visual Domain Adaptation](https://mlsanity.com/paper/2112.07516/) (2021)
- [Modality-Agnostic Debiasing for Single Domain Generalization](https://mlsanity.com/paper/2303.07123/) (2023)
- [Towards Novel Target Discovery Through Open-Set Domain Adaptation](https://mlsanity.com/paper/2105.02432/) (2021)
- [A Novel Mix-normalization Method for Generalizable Multi-source Person Re-identification](https://mlsanity.com/paper/2201.09846/) (2022)
- [Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptation](https://mlsanity.com/paper/2107.02067/) (2021)
- [Controlled Generation of Unseen Faults for Partial and Open-Partial Domain Adaptation](https://mlsanity.com/paper/2204.14068/) (2022)
- [Progressively Select and Reject Pseudo-labelled Samples for Open-Set Domain Adaptation](https://mlsanity.com/paper/2110.12635/) (2021)
- [Trust your Good Friends: Source-free Domain Adaptation by Reciprocal Neighborhood Clustering](https://mlsanity.com/paper/2309.00528/) (2023)
- [Universal Domain Adaptation in Ordinal Regression](https://mlsanity.com/paper/2106.11576/) (2021)
- [OneRing: A Simple Method for Source-free Open-partial Domain Adaptation](https://mlsanity.com/paper/2206.03600/) (2022)
- [IT-RUDA: Information Theory Assisted Robust Unsupervised Domain Adaptation](https://mlsanity.com/paper/2210.12947/) (2022)
- [Towards Adaptive Unknown Authentication for Universal Domain Adaptation by Classifier Paradox](https://mlsanity.com/paper/2207.04494/) (2022)
- [Subtype-Aware Dynamic Unsupervised Domain Adaptation](https://mlsanity.com/paper/2208.07754/) (2022)
- [Explaining Cross-Domain Recognition with Interpretable Deep Classifier](https://mlsanity.com/paper/2211.08249/) (2022)
- [Self-Paced Learning for Open-Set Domain Adaptation](https://mlsanity.com/paper/2303.05933/) (2023)
- [Trustworthy Representation Learning Across Domains](https://mlsanity.com/paper/2308.12315/) (2023)
- [KRADA: Known-region-aware Domain Alignment for Open-set Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2106.06237/) (2021)
- [Contrastive Learning for Cross-Domain Open World Recognition](https://mlsanity.com/paper/2203.09257/) (2022)
- [Out-of-Distribution Detection with Hilbert-Schmidt Independence Optimization](https://mlsanity.com/paper/2209.12807/) (2022)
- [Language-Aware Information Maximization for Transductive Few-Shot CLIP](https://mlsanity.com/paper/2509.00305/) (2025)
- [Generalization Under Scrutiny: Cross-Domain Detection Progresses, Pitfalls, and Persistent Challenges](https://mlsanity.com/paper/2604.08230/) (2026)

## Abstract (arXiv)

Unsupervised domain adaptation has received significant attention in recent years. Most of existing works tackle the closed-set scenario, assuming that the source and target domains share the exactly same categories. In practice, nevertheless, a target domain often contains samples of classes unseen in source domain (i.e., unknown class). The extension of domain adaptation from closed-set to such open-set situation is not trivial since the target samples in unknown class are not expected to align with the source. In this paper, we address this problem by augmenting the state-of-the-art domain adaptation technique, Self-Ensembling, with category-agnostic clusters in target domain. Specifically, we present Self-Ensembling with Category-agnostic Clusters (SE-CC) -- a novel architecture that steers domain adaptation with the additional guidance of category-agnostic clusters that are specific to target domain. These clustering information provides domain-specific visual cues, facilitating the generalization of Self-Ensembling for both closed-set and open-set scenarios. Technically, clustering is firstly performed over all the unlabeled target samples to obtain the category-agnostic clusters, which reveal the underlying data space structure peculiar to target domain. A clustering branch is capitalized on to ensure that the learnt representation preserves such underlying structure by matching the estimated assignment distribution over clusters to the inherent cluster distribution for each target sample. Furthermore, SE-CC enhances the learnt representation with mutual information maximization. Extensive experiments are conducted on Office and VisDA datasets for both open-set and closed-set domain adaptation, and superior results are reported when comparing to the state-of-the-art approaches.