Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Generalized Zero-Shot Recognition Based on Visually Semantic Embedding
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 |
|---|---|---|---|
| use a visually semantic latent part-mixture embedding instead of conventional visual features, with semantic supervision | Ours(S) · CUB GZSL | H | Helped |
| use a visually semantic latent part-mixture embedding instead of conventional visual features, with semantic supervision | Ours(S) · AWA2 GZSL | H | Helped |
| use a visually semantic latent part-mixture embedding instead of conventional visual features, with semantic supervision | Ours(S) · aPY GZSL | H | Helped |
| replace semantic supervision and evaluation with visual-oracle supervision and evaluation | Ours(S) · CUB GZSL | H: 48.4 -> 50.2 | Helped |
| replace semantic supervision and evaluation with visual-oracle supervision and evaluation | Ours(S) · AWA2 GZSL | H: 57.2 -> 60.2 | Helped |
| replace semantic supervision and evaluation with visual-oracle supervision and evaluation | Ours(S) · aPY GZSL | H: 36.6 -> 56.2 | Helped |
| flatten the structured visual representation, removing part-wise structure (ablation) | Ours(Π) · CUB GZSL | H: 50.2 -> 49.6 | Hurt |
| flatten the structured visual representation, removing part-wise structure (ablation) | Ours(Π) · AWA2 GZSL | H: 60.2 -> 57.6 | Hurt |
| flatten the structured visual representation, removing part-wise structure (ablation) | Ours(Π) · aPY GZSL | H: 56.2 -> 51.7 | Hurt |
| use visual-oracle supervision instead of semantic supervision | DEVISE · CUB GZSL | H: 32.8 -> 33.7 | Helped |
| use visual-oracle supervision instead of semantic supervision | DEVISE · AWA2 GZSL | H: 27.8 -> 41.2 | Helped |
| use a structured part-based visual embedding rather than a flattened embedding (ablation) | Ours(Π) · CUB ZSL, standard split | accuracy: 66.8 -> 68.8 | Helped |
Closest papers by meaning
- Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names (CVPR 2024 · similarity 0.92)
- Epsilon: Exploring Comprehensive Visual-Semantic Projection for Multi-Label Zero-Shot Learning (AAAI 2025 · similarity 0.92)
- ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning (AAAI 2025 · similarity 0.92)
- ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning (ICLR 2025 · similarity 0.91)
- Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning (CVPR 2024 · similarity 0.91)
- TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning (NeurIPS 2024 · similarity 0.90)
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.