Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Language-Driven Multi-Label Zero-Shot Learning with Semantic Granularity
Shouwen Wang, Qian Wan, Junbin Gao, Zhigang Zeng
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 |
|---|---|---|---|
| add class name reconstruction (CNR) from LLM descriptions (ablation) | CLIP prompt baseline · MS-COCO ZSL | mAP: 74.6 -> 82.2 | Improved |
| add class name reconstruction (CNR) (ablation) | CLIP prompt baseline · NUS-WIDE ZSL | mAP: 46.5 -> 51.7 | Improved |
| add pair-based loss (PBL) (ablation) | RCNn (CNR) · MS-COCO ZSL | mAP: 82.2 -> 84.1 | Improved |
| add multi-snippet semantic aggregation (MSSA) (ablation) | RCNn (CNR+PBL) · MS-COCO ZSL | mAP: 84.1 -> 86.3 | Improved |
| add PBL and MSSA (ablation) | RCNn · NUS-WIDE GZSL | F1 (Top-3): 19.5 -> 19.3 | No clear effect |
| add pair-based loss (PBL) (ablation) | RCNn (CNR) · NUS-WIDE ZSL | F1 (Top-3): 45.9 -> 47.4 | Improved |
| add MSSA (ablation) | RCNn (CNR+PBL) · NUS-WIDE ZSL | F1 (Top-3): 47.4 -> 48.4 | Improved |
| text-only training with LLM descriptions vs image-trained DualCoOp | RCNn · MS-COCO GZSL, Top-3 | F1: 62.9 -> 60.7 (vs DualCoOp) | Hurt |
| text-only training vs image-trained MKT | RCNn · NUS-WIDE GZSL | mAP: 18.3 -> 17.9 (vs MKT) | Mixed |
| RCNn vs MKT on Open Images ZSL | RCNn · Open Images ZSL | mAP: 68.1 -> 70.2 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- TagCLIP — TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP without Training (AAAI 2024) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Class Semantic Attribute Perception Guided Zero-Shot Learning (AAAI 2025 · similarity 0.90)
- Epsilon: Exploring Comprehensive Visual-Semantic Projection for Multi-Label Zero-Shot Learning (AAAI 2025 · similarity 0.89)
- Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge (NeurIPS 2024 · similarity 0.88)
- ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning (ICLR 2025 · similarity 0.88)
- Language-Driven Cross-Modal Classifier for Zero-Shot Multi-Label Image Recognition (ICML 2024 · similarity 0.88)
- Multi-Label Few-Shot Image Classification via Pairwise Feature Augmentation and Flexible Prompt Learning (AAAI 2025 · similarity 0.88)
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.
