# Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning

arXiv: https://arxiv.org/abs/2303.08566 · HTML: https://mlsanity.com/paper/2303.08566/

## Key facts

- Cited by 74 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 70 references that are in the map.
- First posted on arXiv 15 Mar 2023.

## Builds on (most cited first, 30 of 56)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Towards a Unified View of Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2110.04366/) (2021)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [Intriguing Properties of Vision Transformers](https://mlsanity.com/paper/2105.10497/) (2021)
- [A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark](https://mlsanity.com/paper/1910.04867/) (2019)
- [What is being transferred in transfer learning?](https://mlsanity.com/paper/2008.11687/) (2020)
- [Parameter-Efficient Transfer Learning with Diff Pruning](https://mlsanity.com/paper/2012.07463/) (2020)

## Built on by (most cited first, 30 of 74)

- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning](https://mlsanity.com/paper/2306.07967/) (2023)
- [Efficient Tuning and Inference for Large Language Models on Textual Graphs](https://mlsanity.com/paper/2401.15569/) (2024)
- [Parameter-Efficient Fine-Tuning in Large Models: A Survey of Methodologies](https://mlsanity.com/paper/2410.19878/) (2024)
- [TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems](https://mlsanity.com/paper/2502.02527/) (2025)
- [5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks](https://mlsanity.com/paper/2408.08345/) (2024)
- [AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping](https://mlsanity.com/paper/2505.18738/) (2025)
- [Let the Expert Stick to His Last: Expert-Specialized Fine-Tuning for Sparse Architectural Large Language Models](https://mlsanity.com/paper/2407.01906/) (2024)
- [STA-VPT: SpatioTemporally Aligned Visual Prompt Tuning](https://mlsanity.com/paper/2312.10376/) (2023)
- [DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers](https://mlsanity.com/paper/2505.23694/) (2025)
- [See Further for Parameter Efficient Fine-tuning by Standing on the Shoulders of Decomposition](https://mlsanity.com/paper/2407.05417/) (2024)
- [PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models](https://mlsanity.com/paper/2506.20629/) (2025)
- [Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference](https://mlsanity.com/paper/2405.14700/) (2024)
- [MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba](https://mlsanity.com/paper/2411.03855/) (2024)
- [DemoCaricature: Democratising Caricature Generation with a Rough Sketch](https://mlsanity.com/paper/2312.04364/) (2023)
- [Controllable Prompt Tuning For Balancing Group Distributional Robustness](https://mlsanity.com/paper/2403.02695/) (2024)
- [Generative Active Learning for Long-tailed Instance Segmentation](https://mlsanity.com/paper/2406.02435/) (2024)
- [Expanding Sparse Tuning for Low Memory Usage](https://mlsanity.com/paper/2411.01800/) (2024)
- [PRO-VPT: Distribution-Adaptive Visual Prompt Tuning via Prompt Relocation](https://mlsanity.com/paper/2503.06901/) (2025)
- [KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models](https://mlsanity.com/paper/2412.06071/) (2024)
- [Distribution-Aligned Decoding for Efficient LLM Task Adaptation](https://mlsanity.com/paper/2509.15888/) (2025)
- [MoSA: Mixture of Sparse Adapters for Visual Efficient Tuning](https://mlsanity.com/paper/2312.02923/) (2023)
- [MLAE: Masked LoRA Experts for Visual Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2405.18897/) (2024)
- [Referring Expression Comprehension for Small Objects](https://mlsanity.com/paper/2510.03701/) (2025)
- [TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning](https://mlsanity.com/paper/2501.04293/) (2025)
- [iVPT: Improving Task-relevant Information Sharing in Visual Prompt Tuning by Cross-layer Dynamic Connection](https://mlsanity.com/paper/2404.05207/) (2024)
- [Learning Where to Edit Vision Transformers](https://mlsanity.com/paper/2411.01948/) (2024)
- [F3OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics](https://mlsanity.com/paper/2411.11912/) (2024)
- [Sparsity- and Hybridity-Inspired Visual Parameter-Efficient Fine-Tuning for Medical Diagnosis](https://mlsanity.com/paper/2405.17877/) (2024)
- [iConFormer: Dynamic Parameter-Efficient Tuning with Input-Conditioned Adaptation](https://mlsanity.com/paper/2409.02838/) (2024)

## Abstract (arXiv)

Visual Parameter-Efficient Fine-Tuning (PEFT) has become a powerful alternative for full fine-tuning so as to adapt pre-trained vision models to downstream tasks, which only tunes a small number of parameters while freezing the vast majority ones to ease storage burden and optimization difficulty. However, existing PEFT methods introduce trainable parameters to the same positions across different tasks depending solely on human heuristics and neglect the domain gaps. To this end, we study where to introduce and how to allocate trainable parameters by proposing a novel Sensitivity-aware visual Parameter-efficient fine-Tuning (SPT) scheme, which adaptively allocates trainable parameters to task-specific important positions given a desired tunable parameter budget. Specifically, our SPT first quickly identifies the sensitive parameters that require tuning for a given task in a data-dependent way. Next, our SPT further boosts the representational capability for the weight matrices whose number of sensitive parameters exceeds a pre-defined threshold by utilizing existing structured tuning methods, e.g., LoRA [23] or Adapter [22], to replace directly tuning the selected sensitive parameters (unstructured tuning) under the budget. Extensive experiments on a wide range of downstream recognition tasks show that our SPT is complementary to the existing PEFT methods and largely boosts their performance, e.g., SPT improves Adapter with supervised pre-trained ViT-B/16 backbone by 4.2% and 1.4% mean Top-1 accuracy, reaching SOTA performance on FGVC and VTAB-1k benchmarks, respectively. Source code is at https://github.com/ziplab/SPT