Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Hierarchical Disentanglement of Discriminative Latent Features for Zero-Shot Learning
Check 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 hierarchical disentanglement (ablation) | DLFZRL · SUN, traditional ZSL | average top-1 accuracy: 57.2 -> 59.3 | Helped |
| Add hierarchical disentanglement (ablation) | DLFZRL · CUB, traditional ZSL | average top-1 accuracy: 55.1 -> 57.8 | Helped |
| Add hierarchical disentanglement (ablation) | DLFZRL · AWA1, traditional ZSL | average top-1 accuracy: 57.9 -> 66.3 | Helped |
| Add hierarchical disentanglement (ablation) | DLFZRL · AWA2, traditional ZSL | average top-1 accuracy: 63.1 -> 63.7 | Helped |
| Add hierarchical disentanglement (ablation) | DLFZRL · aPY, traditional ZSL | average top-1 accuracy: 41.6 -> 44.5 | Helped |
| Add hierarchical disentanglement (ablation) | DLFZRL · SUN, generalized ZSL | harmonic mean: 23.2 -> 24.6 | Helped |
| Add hierarchical disentanglement (ablation) | DLFZRL · CUB, generalized ZSL | harmonic mean: 35.4 -> 37.1 | Helped |
| Add hierarchical disentanglement (ablation) | DLFZRL · AWA1, generalized ZSL | harmonic mean: 37.1 -> 40.5 | Helped |
| Add hierarchical disentanglement (ablation) | DLFZRL · AWA2, generalized ZSL | harmonic mean: 40.6 -> 45.1 | Helped |
| Add hierarchical disentanglement (ablation) | DLFZRL · aPY, generalized ZSL | harmonic mean: 30.7 -> 31.0 | Helped |
| Add feature selection (ablation) | DLFZRL · AWA1, traditional ZSL | average top-1 accuracy: 62.9 -> 66.3 | Helped |
| Add feature selection (ablation) | DLFZRL · AWA1, generalized ZSL | harmonic mean: 36.3 -> 40.5 | Helped |
Closest papers by meaning
- Generalized Zero-Shot Learning via Disentangled Representation (AAAI 2021 · similarity 0.91)
- Discriminative Learning of Latent Features for Zero-Shot Recognition (CVPR 2018 · similarity 0.91)
- Distinguishing Unseen From Seen for Generalized Zero-Shot Learning (CVPR 2022 · similarity 0.89)
- Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders (CVPR 2019 · similarity 0.89)
- Class Semantic Attribute Perception Guided Zero-Shot Learning (AAAI 2025 · similarity 0.88)
- TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning (NeurIPS 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.