Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Independent Prototype Propagation for Zero-Shot Compositionality
Frank Ruis, Gertjan J. Burghouts, Doina Bucur
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 HSIC independence loss to visual prototypes (ablation) | ProtoProp · AO-Clevr 4:6 | Harmonic mean: 84.8 -> 96.7 | Improved |
| finetune the backbone instead of freezing it (ablation) | ProtoProp · AO-Clevr 4:6 | Harmonic mean: 75.5 -> 96.7 | Improved |
| use visual prototypes instead of word2vec node features (with independence loss) (ablation) | ProtoProp · AO-Clevr 4:6 | Harmonic mean: 90.4 -> 96.7 | Improved |
| use visual prototypes instead of word2vec node features (without independence loss) (ablation) | ProtoProp · AO-Clevr 4:6 | Harmonic mean: 88.4 -> 84.8 | Hurt |
| add independence loss to semantic-feature variant (ablation) | semantic node features GCN · AO-Clevr 4:6 | Harmonic mean: 88.4 -> 90.4 | Improved |
| propagate independent prototypes through compositional graph (ProtoProp vs CGE) | CZSL baselines · UT-Zappos | Harmonic mean: 47.1 -> 50.2 | Improved |
| ProtoProp vs CGE on closed unseen accuracy | CZSL baselines · UT-Zappos | Closed unseen accuracy: 65.9 -> 65.5 | No clear effect |
| ProtoProp vs Causal as the unseen proportion grows | CZSL baselines · AO-Clevr 7:3 | Harmonic mean: 33.7 -> 54.9 | Improved |
Closest papers by meaning
- Revealing the Proximate Long-Tail Distribution in Compositional Zero-Shot Learning (AAAI 2024 · similarity 0.89)
- Beyond Seen Primitive Concepts and Attribute-Object Compositional Learning (CVPR 2024 · similarity 0.88)
- Retrieval-Augmented Primitive Representations for Compositional Zero-Shot Learning (AAAI 2024 · similarity 0.88)
- A Dynamic Learning Method towards Realistic Compositional Zero-Shot Learning (AAAI 2024 · similarity 0.88)
- Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learning (CVPR 2024 · similarity 0.88)
- Beyond Image Classification: A Video Benchmark and Dual-Branch Hybrid Discrimination Framework for Compositional Zero-Shot Learning (CVPR 2025 · similarity 0.87)
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.
