Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Zero-Shot Learning via Joint Latent Similarity Embedding
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 |
|---|---|---|---|
| Use joint latent similarity embedding instead of SSE-ReLU | Zero-shot recognition · Average across four datasets | accuracy: 4.90% | Helped |
| Adapt the joint latent similarity method for retrieval instead of SSE | Zero-shot retrieval · Average across four datasets | mAP: 22.45% | Helped |
| Add dictionary learning, test-time unseen-embedding estimation, and the proposed prediction rule (ablation) | Zero-shot recognition system · Average across four datasets | accuracy: 58.81 -> 62.51 | Helped |
| Include the source-domain fit term in the prediction rule (ablation) | Zero-shot recognition system · Average across four datasets | accuracy: 58.81 -> 60.20 | Helped |
| Add dictionary learning while retaining initial unseen embeddings (ablation) | Zero-shot recognition system · Average across four datasets | accuracy: 58.81 -> 59.91 | Helped |
| Estimate unseen-class latent embeddings at test time rather than using initial embeddings (ablation) | Zero-shot recognition system · Average across four datasets | accuracy: 59.91 -> 62.51 | Helped |
| Include the source-domain fit term in prediction (ablation) | Zero-shot recognition system · aP&Y | accuracy: 39.13±2.35 -> 38.94±2.27 | Hurt |
| Use joint latent similarity embeddings rather than SSE-INT | Zero-shot retrieval · AwA | mAP: 46.25 -> 67.66 | Helped |
Closest papers by meaning
- Zero-Shot Recognition via Direct Classifier Learning with Transferred Samples and Pseudo Labels (AAAI 2017 · similarity 0.91)
- Discriminative Learning of Latent Features for Zero-Shot Recognition (CVPR 2018 · similarity 0.91)
- Latent Embeddings for Zero-Shot Classification (CVPR 2016 · similarity 0.91)
- Dual-View Ranking with Hardness Assessment for Zero-Shot Learning (AAAI 2019 · similarity 0.90)
- Transductive Zero-Shot Recognition via Shared Model Space Learning (AAAI 2016 · similarity 0.90)
- Preserving Semantic Relations for Zero-Shot Learning (CVPR 2018 · 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.