Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Deep Semantic Structural Constraints for Zero-Shot Learning
Read the paperCheck 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 |
|---|---|---|---|
| Fine-tune the CNN end-to-end instead of keeping image features fixed (ablation) | Baseline ZSL model · CUB | accuracy (%): 50.31 -> 58.26 | Helped |
| Add Image Feature Structure constraint (triplet loss on image features) (ablation) | Baseline · SUN | accuracy (%): 58.75 -> 60.21 | Helped |
| Add Image Feature Structure constraint (ablation) | Baseline · CUB | accuracy (%): 58.26 -> 58.80 | No clear effect |
| Add Semantic Embedding Structure constraint (relaxed triplet with adaptive margin) (ablation) | Baseline · CUB | accuracy (%): 58.26 -> 64.54 | Helped |
| Add SESc (ablation) | Baseline · AwA | accuracy (%): 75.19 -> 76.89 | Helped |
| Combine IFSc and SESc (full DSSC) (ablation) | Deep-SESc · CUB | accuracy (%): 64.54 -> 65.99 | Helped |
| Use self-adaptive margin in SESc instead of fixed margin 1.0 (ablation) | Deep-SESc · AwA | accuracy (%): 73.64 -> 76.89 | Helped |
| Use self-adaptive margin in SESc instead of fixed margin (ablation) | Deep-SESc · CUB | accuracy (%): 62.29 -> 64.54 | Helped |
| DSSC vs SAE reported results | DSSC · AwA | accuracy (%): 84.7 -> 78.51 | Hurt |
| DSSC vs SCoRe | DSSC · CUB | accuracy (%): 58.4 -> 65.99 | Helped |
Closest papers by meaning
- ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning (AAAI 2025 · similarity 0.88)
- Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learning (CVPR 2025 · similarity 0.88)
- S3A: Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment (AAAI 2024 · similarity 0.88)
- Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning (CVPR 2024 · similarity 0.87)
- Class Semantic Attribute Perception Guided Zero-Shot Learning (AAAI 2025 · similarity 0.87)
- Data-Free Generalized Zero-Shot Learning (AAAI 2024 · 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.