Research map / Label-efficient and robust learning / Domain adaptation and generalization
Learning to Cluster under Domain Shift
Willi Menapace, Stéphane Lathuilière, Elisa Ricci
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| lower the alpha smoothing parameter from 1.0 to 0.1 when estimating the cluster probability matrix (ablation) | proposed clustering model (training without target adaptation) · Office31 (all domains as source) | accuracy (%): +5.8% average accuracy | Improved |
| lower alpha further below 0.1 (ablation) | proposed clustering model · Office31 (all domains as source) | accuracy (%) | Hurt |
| use ACIDS target adaptation instead of plain mutual information maximization (ablation) | proposed clustering model · PACS Cartoon target | target accuracy | Improved |
| use ACIDS target adaptation instead of plain mutual information maximization (ablation) | proposed clustering model · PACS Sketch target | target accuracy | No clear effect |
| add mutual information loss for feature alignment (ablation) | proposed clustering model · PACS Cartoon target (t-SNE) | qualitative domain alignment | Improved |
Closest papers by meaning
- GeCC: Generalized Contrastive Clustering with Domain Shifts Modeling (AAAI 2025 · similarity 0.84)
- Quickshift++: Provably Good Initializations for Sample-Based Mean Shift (ICML 2018 · similarity 0.83)
- Domain Consensus Clustering for Universal Domain Adaptation (CVPR 2021 · similarity 0.83)
- Automated Clustering of High-dimensional Data with a Feature Weighted Mean Shift Algorithm (AAAI 2021 · similarity 0.83)
- Contrastive Mean-Shift Learning for Generalized Category Discovery (CVPR 2024 · similarity 0.81)
- Clustering Properties of Self-Supervised Learning (ICML 2025 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
