Research map / Vision-language and multimodal / CLIP and zero-shot
Less Is More: Zero-Shot Learning From Online Textual Documents With Noise Suppression
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 |
|---|---|---|---|
| Add l2,1-norm noise suppression to the text-to-image matching model | Text-based zero-shot learning · AwA | Mean Accuracy: 24.82 -> $29.12 \pm 0.07$ | Helped |
| Add l2,1-norm noise suppression to the text-to-image matching model | Text-based zero-shot learning · CUB-200-2011 | Top-1 Acc: 23.80 -> $29.00 \pm 0.28$ | Helped |
| Use binarized word histograms instead of TF-IDF (ablation) | Text-based zero-shot learning · AwA | Performance: about 7% | Helped |
| Use binarized word histograms instead of TF-IDF (ablation) | Text-based zero-shot learning · CUB-200-2011 | Performance: 5% | Helped |
| Replace the l2,1-norm with a Frobenius norm (ablation) | Text-based zero-shot learning · AwA and CUB-200-2011 | Zero-shot classification performance | Hurt |
| Manually remove document dimensions with low importance weights (ablation) | Text-based zero-shot learning · AwA and CUB-200-2011 | Zero-shot classification performance | Hurt |
| Use TF-IDF weights rather than a binarized word representation (ablation) | Text-based zero-shot learning · AwA and CUB-200-2011 | Performance: about 7% and 5% | Hurt |
Closest papers by meaning
- Liberating Seen Classes: Boosting Few-Shot and Zero-Shot Text Classification via Anchor Generation and Classification Reframing (AAAI 2024 · similarity 0.85)
- Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models (NeurIPS 2025 · similarity 0.85)
- Data-Free Generalized Zero-Shot Learning (AAAI 2024 · similarity 0.85)
- ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning (ICLR 2025 · similarity 0.85)
- Zero-Shot Robustification of Zero-Shot Models (ICLR 2024 · similarity 0.84)
- Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions (CVPR 2024 · similarity 0.84)
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.