# Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference

arXiv: https://arxiv.org/abs/2405.14700 · HTML: https://mlsanity.com/paper/2405.14700/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 73 references that are in the map.
- First posted on arXiv 23 May 2024.

## Builds on (most cited first, 30 of 55)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [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)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [Scaling Vision Transformers to 22 Billion Parameters](https://mlsanity.com/paper/2302.05442/) (2023)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [Masked Autoencoders As Spatiotemporal Learners](https://mlsanity.com/paper/2205.09113/) (2022)
- [A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark](https://mlsanity.com/paper/1910.04867/) (2019)

## Built on by (most cited first, 12 of 12)

- [Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model](https://mlsanity.com/paper/2411.10803/) (2024)
- [SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning](https://mlsanity.com/paper/2505.22596/) (2025)
- [Shifting AI Efficiency From Model-Centric to Data-Centric Compression](https://mlsanity.com/paper/2505.19147/) (2025)
- [Variation-aware Vision Token Dropping for Faster Large Vision-Language Models](https://mlsanity.com/paper/2509.01552/) (2025)
- [M2IST: Multi-Modal Interactive Side-Tuning for Efficient Referring Expression Comprehension](https://mlsanity.com/paper/2407.01131/) (2024)
- [SwimVG: Step-wise Multimodal Fusion and Adaption for Visual Grounding](https://mlsanity.com/paper/2502.16786/) (2025)
- [MaPPER: Multimodal Prior-guided Parameter Efficient Tuning for Referring Expression Comprehension](https://mlsanity.com/paper/2409.13609/) (2024)
- [TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning](https://mlsanity.com/paper/2507.22872/) (2025)
- [KARST: Multi-Kernel Kronecker Adaptation with Re-Scaling Transmission for Visual Classification](https://mlsanity.com/paper/2502.06779/) (2025)
- [Deploying Large AI Models on Resource-Limited Devices with Split Federated Learning](https://mlsanity.com/paper/2504.09114/) (2025)
- [EvoMail: Self-Evolving Cognitive Agents for Adaptive Spam and Phishing Email Defense](https://mlsanity.com/paper/2509.21129/) (2025)
- [Decoupled Multi-Predictor Optimization for Inference-Efficient Model Tuning](https://mlsanity.com/paper/2511.03245/) (2025)

## Abstract (arXiv)

Parameter-efficient fine-tuning (PEFT) has emerged as a popular solution for adapting pre-trained Vision Transformer (ViT) models to downstream applications by updating only a small subset of parameters. While current PEFT methods have achieved fine-tuning efficiency, they overlook the efficiency of computation and GPU memory during inference, falling short of practical requirements. To address this limitation, we propose Sparse-Tuning, an efficient and effective framework that leverages popular token sparsification (TS) techniques to reduce information redundancy in images and videos, thereby significantly improving computational and memory efficiency. However, TS often compromises performance due to inevitable information loss. To address this limitation, we further introduce Dense Adapters (DA) to compensate for the information losses incurred by token sparsification. DA integrates comprehensive token information from shallow layers into the retained tokens of deeper layers, ensuring minimal performance degradation. Through the integration of TS techniques and DA, Sparse-Tuning achieves a significant reduction in computation and memory overhead while maintaining performance. Empirical results on VTAB-1K, three image datasets, and two video datasets show that Sparse-Tuning reduces GFLOPs to 66% of the original ViT-B while achieving state-of-the-art performance compared to full fine-tuning and other PEFT baselines.