Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Learning Discriminative Latent Attributes for Zero-Shot Classification
Huajie Jiang, Ruiping Wang, Shiguang Shan, Yi Yang, Xilin Chen
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 the discriminative seen-class classifier constraint to the latent attribute dictionary (LA- to LA) (ablation) | LAD · aP&Y | accuracy | Improved |
| learn latent attributes (linear combinations of attributes) instead of the attribute dictionary alone or the similarity space alone (ablation) | LAD · aP&Y | accuracy | Improved |
| combine latent attribute space with similarity space (LA to LAS) (ablation) | LAD · aP&Y | multi-class accuracy (%): 51.13 -> 53.74 | Improved |
| combine latent attribute space with similarity space (LA to LAS) (ablation) | LAD · AwA | multi-class accuracy (%): 80.49 -> 82.48 | Improved |
| combine latent attribute space with similarity space (LA to LAS) (ablation) | LAD · CUB-200 | multi-class accuracy (%): 56.36 -> 56.63 | Improved |
| combine latent attribute space with similarity space (LA to LAS) (ablation) | LAD · SUN-A | multi-class accuracy (%): 83.50 -> 85.00 | Improved |
| use latent attribute dictionary versus SSE-ReLU on fine-grained CUB-200 | LAD (LAS) · CUB-200 | multi-class accuracy (%): 30.41 -> 56.63 | Improved |
| use LAD (LAS) versus JSLA, which models user-defined and discriminative attributes separately | LAD (LAS) · AwA | multi-class accuracy (%): 82.81 -> 82.48 | Hurt |
| use LAD (LAS) versus Bucher et al. metric-learning ZSL | LAD (LAS) · aP&Y | multi-class accuracy (%): 53.15 -> 53.74 | Improved |
Closest papers by meaning
- Discriminative Learning of Latent Features for Zero-Shot Recognition (CVPR 2018 · similarity 0.92)
- Attribute Attention for Semantic Disambiguation in Zero-Shot Learning (ICCV 2019 · similarity 0.91)
- Joint Dictionaries for Zero-Shot Learning (AAAI 2018 · similarity 0.91)
- Attributes2Classname: A Discriminative Model for Attribute-Based Unsupervised Zero-Shot Learning (ICCV 2017 · similarity 0.91)
- Zero-Shot Learning via Joint Latent Similarity Embedding (CVPR 2016 · similarity 0.91)
- Class Semantic Attribute Perception Guided Zero-Shot Learning (AAAI 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.
