Research map / Label-efficient and robust learning / Domain adaptation and generalization
ORIENT: Submodular Mutual Information Measures for Data Subset Selection under Distribution Shift
Athresh Karanam, Krishnateja Killamsetty, Harsha Kokel, Rishabh K Iyer
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 |
|---|---|---|---|
| replace Full source training with ORIENT (FLMI) subset (30%) | CCSA · Office-31 A->W | accuracy: 0.72 -> 0.76 | Improved |
| replace Full source training with ORIENT (FLMI) subset (30%) | CCSA · Office-31 D->W | accuracy: 0.93 -> 0.89 | Hurt |
| replace Random subset with ORIENT (FLMI) subset | CCSA · Office-31 D->W | accuracy: 0.81 -> 0.89 | Improved |
| replace Random subset with ORIENT (FLMI) subset | d-SNE · Office-31 D->W | accuracy: 0.86 -> 0.90 | Improved |
| replace Full source training with ORIENT (FLMI) subset | d-SNE · Office-31 D->A | accuracy: 0.53 -> 0.55 | Improved |
| replace Full source training with ORIENT (FLMI) subset | CCSA · Office-Home R->P | accuracy: 0.74 -> 0.78 | Improved |
| replace Random subset with ORIENT (FLMI) subset | CCSA · Office-Home R->C | accuracy: 0.47 -> 0.54 | Improved |
| replace Full source training with ORIENT (FLMI) subset | CCSA · Office-Home C->P | accuracy: 0.67 -> 0.71 | Improved |
| replace Full source training with ORIENT (FLMI) subset | CCSA · Office-Home R->A | accuracy: 0.57 -> 0.59 | Improved |
| replace Full source training with ORIENT (FLMI) subset | d-SNE · Office-Home A->R | accuracy: 0.63 -> 0.61 | Hurt |
| replace Full source training with ORIENT (FLMI) subset | d-SNE · Office-Home P->R | accuracy: 0.62 -> 0.63 | No clear effect |
| use 30% subset selected by ORIENT instead of full source data | ORIENT (FLMI) with d-SNE · Office-31 and Office-Home | training speedup: ~3× | Improved |
Closest papers by meaning
- Causal meets Submodular: Subset Selection with Directed Information (NeurIPS 2016 · similarity 0.86)
- Transferable Query Selection for Active Domain Adaptation (CVPR 2021 · similarity 0.85)
- Towards Reliable Model Selection for Unsupervised Domain Adaptation: An Empirical Study and A Certified Baseline (NeurIPS 2024 · similarity 0.85)
- Source-Free Domain Adaptation via Target Prediction Distribution Searching (IJCV 2023 · similarity 0.85)
- Gradient-Based Sample Selection for Black-Box Universal Domain Adaptation (AAAI 2025 · similarity 0.84)
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety (CVPR 2025 · similarity 0.84)
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.
