Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Attributes2Classname: A Discriminative Model for Attribute-Based Unsupervised Zero-Shot Learning
Berkan Demirel, Ramazan Gokberk Cinbis, Nazli Ikizler-Cinbis
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 |
|---|---|---|---|
| learn word transform with predicate matrix (PBT) (ablation) | GloVe class embeddings · AwA | normalized accuracy: 10.2 -> 60.7 | Improved |
| learn word transform with predicate matrix (PBT) (ablation) | GloVe class embeddings · aPaY | normalized accuracy: 16.0 -> 29.4 | Improved |
| learn word transform with images (IBT) instead of identity (ablation) | GloVe class embeddings · AwA | normalized accuracy: 10.2 -> 69.9 | Improved |
| learn word transform with images (IBT) instead of identity (ablation) | GloVe class embeddings · aPaY | normalized accuracy: 16.0 -> 38.2 | Improved |
| image-based instead of predicate-based training (ablation) | word transform · AwA | normalized accuracy: 60.7 -> 69.9 | Improved |
| image-based instead of predicate-based training (ablation) | word transform · aPaY | normalized accuracy: 29.4 -> 38.2 | Improved |
| add external class names and predicate matrix to training (text-only) (ablation) | PBT · AwA | normalized accuracy: 60.7 -> 63.0 | Improved |
| train on external class names only, no AwA classes (ablation) | PBT · AwA | normalized accuracy: 44.0 | Improved |
| use pre-trained GloVe vectors instead of uniform random vectors (ablation) | PBT · AwA | top-1 accuracy: 28.6 | Improved |
| use pre-trained GloVe vectors instead of uniform random vectors (ablation) | IBT · AwA | top-1 accuracy: 13.6 | Improved |
Closest papers by meaning
- Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning (CVPR 2016 · similarity 0.91)
- Learning Discriminative Latent Attributes for Zero-Shot Classification (ICCV 2017 · similarity 0.91)
- SimZSL: Zero-Shot Learning Beyond a Pre-defined Semantic Embedding Space (IJCV 2025 · similarity 0.90)
- VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning (CVPR 2022 · similarity 0.90)
- Fine-Grained Generalized Zero-Shot Learning via Dense Attribute-Based Attention (CVPR 2020 · similarity 0.89)
- Class Semantic Attribute Perception Guided Zero-Shot Learning (AAAI 2025 · similarity 0.89)
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.
