Research map / Label-efficient and robust learning / Recognition and long-tail
Holistic Optimal Label Selection for Robust Prompt Learning under Partial Labels
Yaqi Zhao, Haoliang Sun, Yating Wang, Yongshun Gong, Yilong Yin
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 |
|---|---|---|---|
| use HopS instead of best baseline at extreme confusion | CoOp uni-prompt · Caltech (rand, gamma_c=0.90) | accuracy (%): 87.1 -> 89.5 | Improved |
| use HopS instead of SCE under severe confusion | CoOp uni-prompt · Food (rand, gamma_c=0.90) | accuracy (%): 30.8 -> 65.0 | Improved |
| use HopS instead of CC | CoOp uni-prompt · OxfordPets (rand, gamma_c=0.90) | accuracy (%): 74.2 -> 80.5 | Improved |
| use HopS instead of CC | CoOp uni-prompt · FGVCAircraft (rand, gamma_c=0.90) | accuracy (%): 20.4 -> 19.3 | Hurt |
| use HopS instead of RC | CoOp cls-prompts · OxfordPets (rand, gamma_c=0.90) | accuracy (%): 76.3 -> 70.2 | Hurt |
| use HopS instead of CroSel (trained on full data) | HopS 16-shot · Caltech (insd, gamma_c=0.80) | accuracy (%): 11.8 -> 38.9 | Improved |
| use HopS instead of Papi (trained on full data) | HopS 16-shot · Caltech (rand, gamma_c=0.80) | accuracy (%): 52.2 -> 89.5 | Improved |
| use HopS instead of LWC under instance-dependent confusion | CoOp uni-prompt · Flowers (insd, R18, gamma_c=0.80) | accuracy (%): 28.5 -> 69.9 | Improved |
| use HopS instead of CC | CoOp uni-prompt · Caltech (insd, CLIP candidates, gamma_c=0.80) | accuracy (%): 46.2 -> 45.0 | Hurt |
| add local (LDF) and global (GOP) modules jointly instead of stand-alone (ablation) | HopS · Food (uni-prompt, gamma_c 0.67 and 0.80) | GT label identification accuracy | Improved |
| balance loss weight lambda between local and global signals (0.5, 1.0, 2.0) (ablation) | HopS · eight datasets | accuracy (%) | Improved |
| use neighbor-based refinement instead of confidence-based or graph-based (ablation) | LDF · partial-label datasets | accuracy (%) | Improved |
Closest papers by meaning
- NLPrompt: Noise-Label Prompt Learning for Vision-Language Models (CVPR 2025 · similarity 0.88)
- JoAPR: Cleaning the Lens of Prompt Learning for Vision-Language Models (CVPR 2024 · similarity 0.88)
- Active Prompt Learning in Vision Language Models (CVPR 2024 · similarity 0.86)
- Beyond Words: Augmenting Discriminative Richness via Diffusions in Unsupervised Prompt Learning (CVPR 2025 · similarity 0.86)
- ProAPO: Progressively Automatic Prompt Optimization for Visual Classification (CVPR 2025 · similarity 0.85)
- Making Large Vision Language Models to Be Good Few-Shot Learners (AAAI 2025 · similarity 0.85)
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.
