Research map / Detection and segmentation / Open-set and few-shot detection
Learning the Redundancy-Free Features for Generalized Zero-Shot Object Recognition
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 redundancy-free feature generation instead of GMN | GZSL feature generation · AWA | H: 65.8 -> 66.5 | Helped |
| Use redundancy-free feature generation instead of SABR | GZSL feature generation · CUB | H: 56.8 -> 54.6 | Hurt |
| Use redundancy-free feature generation instead of SABR | GZSL feature generation · SUN | H: 41.5 -> 41.9 | Helped |
| Use redundancy-free feature generation instead of LisGAN | GZSL feature generation · FLO | H: 68.3 -> 71.1 | Helped |
| Add redundancy-free features to semantic embedding | SJE-based GZSL semantic embedding · AWA | H: 19.6 -> 34.8 | Helped |
| Add redundancy-free features to semantic embedding | SJE-based GZSL semantic embedding · CUB | H: 33.6 -> 36.9 | Helped |
| Add redundancy-free features to semantic embedding | SJE-based GZSL semantic embedding · SUN | H: 19.8 -> 27.3 | Helped |
| Add redundancy-free features to semantic embedding | SJE-based GZSL semantic embedding · FLO | H: 21.5 -> 36.3 | Helped |
| Increase the number of synthetic samples per unseen class (ablation) | RFF-GZSL · AWA, CUB, SUN, and FLO | U and H | Helped |
| Increase the redundancy-free feature dimension (ablation) | RFF-GZSL · AWA, CUB, SUN, and FLO | GZSL performance | Helped |
Closest papers by meaning
- On Zero-Shot Recognition of Generic Objects (CVPR 2019 · similarity 0.88)
- TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning (NeurIPS 2024 · similarity 0.88)
- Context-Aware Zero-Shot Recognition (AAAI 2020 · similarity 0.88)
- Data-Free Generalized Zero-Shot Learning (AAAI 2024 · similarity 0.87)
- Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions (CVPR 2024 · similarity 0.87)
- Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names (CVPR 2024 · similarity 0.86)
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.