Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Domain-Invariant Projection Learning for Zero-Shot Recognition
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 transductive learning with unlabelled unseen-class data to the bidirectional DIPL0 model (ablation) | DIPL0 · Pure ZSL, four medium-scale datasets | accuracy (%): 5% to 30% | Helped |
| Add superclass-based alignment (ablation) | DIPL1 · Pure ZSL, four medium-scale datasets | accuracy (%): about 1--2% | Helped |
| Add forward projection alongside reverse projection (ablation) | RPL · Pure ZSL, four medium-scale datasets | accuracy (%): 2--4% | Helped |
| Replace the min-min formulation with a softmax-based soft assignment (ablation) | DIPL · Zero-shot recognition | performance | Hurt |
| Use the full DIPL model rather than the strongest reported baseline | Zero-shot recognition · AwA, CUB, aPY, SUN, and ImNet, standard ZSL | accuracy or hit@5 accuracy (%): 96.1 vs 95.0; 68.2 vs 67.7; 87.8 vs 69.7; 93.5 vs 91.5; 70.0 vs 69.6; 31.7 vs 27.2 | Helped |
| Use the full DIPL model rather than the strongest reported baseline | Zero-shot recognition · AwA, CUB, aPY, and SUN, pure ZSL | accuracy (%): 85.6 vs 68.2; 65.4 vs 58.1; 69.6 vs 44.8; 67.9 vs 60.0 | Helped |
| Use the full DIPL model rather than the strongest reported baseline | Zero-shot recognition · AwA and CUB, generalized ZSL | HM (%): 75.6 vs 52.8; 43.2 vs 39.2 | Helped |
Closest papers by meaning
- Transductive Zero-Shot Learning with Visual Structure Constraint (NeurIPS 2019 · similarity 0.91)
- Context-Aware Zero-Shot Learning for Object Recognition (ICML 2019 · similarity 0.91)
- On Zero-Shot Recognition of Generic Objects (CVPR 2019 · similarity 0.90)
- ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning (AAAI 2025 · similarity 0.89)
- ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning (ICLR 2025 · similarity 0.89)
- Data-Free Generalized Zero-Shot Learning (AAAI 2024 · 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.