Research map / Label-efficient and robust learning / Domain adaptation and generalization
Open Set Domain Adaptation for Image and Action Recognition
Pau Panareda Busto, Ahsan Iqbal, Jüergen Gall
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 |
|---|---|---|---|
| add assign-and-transform-iteratively domain adaptation (ATI) over source-only LSVM | LSVM · Office OS (unsup, all samples) | accuracy: 68.3 -> 82.6 | Improved |
| add outlier rejection (lambda) to ATI (ablation) | ATI · Office OS (unsup, 5 splits) | accuracy: 81.5 -> 82.3 | Improved |
| add outlier rejection (lambda) to ATI (ablation) | ATI · Office CS (unsup, all samples) | accuracy: 93.8 -> 93.7 | No clear effect |
| add locality-constrained assignment with 1 neighbour to ATI-λ in unsupervised setting (ablation) | ATI-λ · Office OS (unsup, all samples) | accuracy: 82.9 -> 81.3 | Hurt |
| add locality-constrained assignment with 1 neighbour to ATI-λ in semi-supervised setting (ablation) | ATI-λ · Office OS (semi-sup) | accuracy: 85.7 -> 86.0 | Improved |
| include the unknown class in the label set C (ablation) | ATI-λ · Office OS (unsup, all samples) | accuracy: 82.3 -> 82.9 | Improved |
| use open set SVM instead of linear SVM on transformed source (ablation) | ATI-λ · Office OS (unsup, all samples) | accuracy: 82.9 -> 75.0 | Hurt |
| increase number of unknown samples from 20 to 400 (ablation) | LSVM · Amazon->DSLR+Webcam OS | accuracy: 74.2 -> 48.2 | Hurt |
| increase number of unknown samples from 20 to 400 (ablation) | ATI-λ · Amazon->DSLR+Webcam OS | accuracy: 80.3 -> 81.9 | No clear effect |
| lower rho towards 0 (more outlier rejection) (ablation) | ATI-λ · Office OS (unsup) | accuracy | Hurt |
| add constraint that every class gets at least one assigned target sample (ablation) | ATI-λ · Office OS (unsup) | accuracy | Improved |
| use VGG-16 features instead of AlexNet | ATI-λ · VISDA->Pascal3D OS | accuracy: 61.4 -> 71.9 | Improved |
Closest papers by meaning
- Open Set Domain Adaptation (ICCV 2017 · similarity 0.93)
- LEARNING FACTORIZED REPRESENTATIONS FOR OPEN-SET DOMAIN ADAPTATION (ICLR 2019 · similarity 0.91)
- Separate to Adapt: Open Set Domain Adaptation via Progressive Separation (CVPR 2019 · similarity 0.90)
- Category-Aware Active Domain Adaptation (ICML 2024 · similarity 0.88)
- Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithm (AAAI 2025 · similarity 0.88)
- A Theory of Learning Unified Model via Knowledge Integration from Label Space Varying Domains (CVPR 2025 · similarity 0.88)
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.
