Research map / Architectures and efficiency / Pruning and efficient tuning
Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning
Haoyu He, Jianfei Cai, Jing Zhang, Dacheng Tao, Bohan Zhuang
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 |
|---|---|---|---|
| allocate trainable parameters by sensitivity (task-specific positions) with Adapter-8 on sensitive matrices (ablation) | Adapter-8 · VTAB-1k mean (supervised ViT-B/16) | top-1 accuracy (%): 73.9 -> 75.5 | Improved |
| add unstructured tuning of sensitive connections to structured tuning (ablation) | SPT-Adapter · VTAB-1k mean (supervised ViT-B/16) | top-1 accuracy (%): 75.5 -> 75.8 | Improved |
| add structured tuning to unstructured tuning (ablation) | SPT-Adapter · VTAB-1k Structured | top-1 accuracy (%): 59.6 -> 60.8 | Improved |
| apply sensitivity criterion to pick matrices for Deep Prompt, Adapter-32, LoRA-16 (ablation) | Deep Prompt, Adapter-32, LoRA-16 · VTAB-1k (supervised ViT-B/16) | mean top-1 accuracy (%): +1.1%, +1.6%, +0.8% | Improved |
| reduce number of samples C for sensitivity from 800 to 400 (ablation) | SPT-LoRA · VTAB-1k mean (supervised ViT-B/16) | top-1 accuracy (%): 76.4 -> 76.4 | No clear effect |
| apply SPT to self-supervised MAE backbone | Adapter / LoRA · VTAB-1k mean (MAE ViT-B/16) | top-1 accuracy (%): 64.8 -> 69.8 | Improved |
| use unstructured sparse-gradient tuning in SPT-LoRA (ablation) | SPT-LoRA · VTAB-1k (ViT-B/16) | fine-tuning memory (GB): 8.3 -> 9.8 | Hurt |
| apply SPT to Adapter on FGVC | Adapter-8 · FGVC mean (supervised ViT-B/16) | top-1 accuracy (%): 85.5 -> 89.5 | Improved |
Closest papers by meaning
- Sensitivity-Aware Efficient Fine-Tuning via Compact Dynamic-Rank Adaptation (CVPR 2025 · similarity 0.94)
- Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition (CVPR 2025 · similarity 0.94)
- Strong Baselines for Parameter-Efficient Few-Shot Fine-Tuning (AAAI 2024 · similarity 0.90)
- Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model (CVPR 2024 · similarity 0.89)
- SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors (NeurIPS 2024 · similarity 0.89)
- Expanding Sparse Tuning for Low Memory Usage (NeurIPS 2024 · 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.
