Research map / Label-efficient and robust learning / Recognition and long-tail
Understanding and Improving Visual Prompting: A Label-Mapping Perspective
Aochuan Chen, Yuguang Yao, Pin-Yu Chen, Yihua Zhang, Sijia Liu
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 |
|---|---|---|---|
| alternate source-label remapping with visual-prompt optimization | visual prompting with ResNet-18 (ImageNet-1K) · Flowers102 | accuracy: 7.9% | Improved |
| alternate source-label remapping with visual-prompt optimization | visual prompting with ResNet-18 (ImageNet-1K) · CIFAR100 | accuracy: 6.7% | Improved |
| alternate source-label remapping with visual-prompt optimization | visual prompting with ResNet-18 (ImageNet-1K) · GTSRB | accuracy: 6.5% | Improved |
| alternate source-label remapping with visual-prompt optimization | visual prompting with ResNet-18 (ImageNet-1K) · CIFAR10 | accuracy | Hurt |
| use iterative label mapping to select context templates rather than one fixed template | CLIP visual prompting · Flowers102 | accuracy: 13.7% | Improved |
| use iterative label mapping to select context templates rather than one fixed template | CLIP visual prompting · DTD | accuracy: 7.1% | Improved |
| increase target training dataset size | ILM-VP versus FLM-VP on GTSRB · GTSRB | accuracy | Improved |
| use ILM-VP instead of FLM-VP | visual prompting across target datasets · datasets with larger target label spaces | accuracy | Improved |
| use ResNet-50 rather than ResNet-18 as the VP source model | visual prompting · Flowers102, EuroSAT, CIFAR100, and ABIDE | accuracy | Hurt |
Closest papers by meaning
- AutoVP: An Automated Visual Prompting Framework and Benchmark (ICLR 2024 · similarity 0.92)
- Enhancing Visual Prompting through Expanded Transformation Space and Overfitting Mitigation (NeurIPS 2025 · similarity 0.91)
- VP-Bench: A Comprehensive Benchmark for Visual Prompting in Multimodal Large Language Models (AAAI 2026 · similarity 0.90)
- SA²VP: Spatially Aligned-and-Adapted Visual Prompt (AAAI 2024 · similarity 0.90)
- LaViP: Language-Grounded Visual Prompting (AAAI 2024 · similarity 0.90)
- Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning (ICML 2024 · 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.
