# 5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks

arXiv: https://arxiv.org/abs/2408.08345 · HTML: https://mlsanity.com/paper/2408.08345/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 75 references that are in the map.
- First posted on arXiv 15 Aug 2024.

## Builds on (most cited first, 30 of 42)

- [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)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [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)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects](https://mlsanity.com/paper/2004.02806/) (2020)
- [Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping](https://mlsanity.com/paper/2002.06305/) (2020)
- [Recent Advances in Convolutional Neural Networks](https://mlsanity.com/paper/1512.07108/) (2015)
- [Prompt-aligned Gradient for Prompt Tuning](https://mlsanity.com/paper/2205.14865/) (2022)
- [VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks](https://mlsanity.com/paper/2112.06825/) (2021)
- [Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning](https://mlsanity.com/paper/2210.08823/) (2022)
- [Oriented R-CNN for Object Detection](https://mlsanity.com/paper/2108.05699/) (2021)
- [Understanding and Improving Layer Normalization](https://mlsanity.com/paper/1911.07013/) (2019)
- [Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges](https://mlsanity.com/paper/2102.12219/) (2021)
- [R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object](https://mlsanity.com/paper/1908.05612/) (2019)
- [To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks](https://mlsanity.com/paper/1903.05987/) (2019)

## Built on by (most cited first, 30 of 34)

- [Parameter-Efficient Fine-Tuning for Foundation Models](https://mlsanity.com/paper/2501.13787/) (2025)
- [SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation](https://mlsanity.com/paper/2505.21795/) (2025)
- [Adapting Vision-Language Foundation Model for Next Generation Medical Ultrasound Image Analysis](https://mlsanity.com/paper/2506.08849/) (2025)
- [Q-Adapter: Visual Query Adapter for Extracting Textually-related Features in Video Captioning](https://mlsanity.com/paper/2510.10022/) (2025)
- [DroneFINE: Domain-Aware Parameter-Efficient Fine-Tuning of Vision-Language Detectors for Drone Images](https://mlsanity.com/paper/2607.00338/) (2026)
- [AdaptGCD: Multi-Expert Adapter Tuning for Generalized Category Discovery](https://mlsanity.com/paper/2410.21705/) (2024)
- [SAM-Based Building Change Detection with Distribution-Aware Fourier Adaptation and Edge-Constrained Warping](https://mlsanity.com/paper/2504.12619/) (2025)
- [DAPE: Dual-Stage Parameter-Efficient Fine-Tuning for Consistent Video Editing with Diffusion Models](https://mlsanity.com/paper/2505.07057/) (2025)
- [MuSASplat: Efficient Sparse-View 3D Gaussian Splats via Lightweight Multi-Scale Adaptation](https://mlsanity.com/paper/2512.07165/) (2025)
- [GFRRN: Explore the Gaps in Single Image Reflection Removal](https://mlsanity.com/paper/2602.22695/) (2026)
- [IV-tuning: Parameter-Efficient Transfer Learning for Infrared-Visible Tasks](https://mlsanity.com/paper/2412.16654/) (2024)
- [GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation](https://mlsanity.com/paper/2506.02882/) (2025)
- [MGDFIS: Multi-scale Global-detail Feature Integration Strategy for Small Object Detection](https://mlsanity.com/paper/2506.12697/) (2025)
- [Swin-TUNA : A Novel PEFT Approach for Accurate Food Image Segmentation](https://mlsanity.com/paper/2507.17347/) (2025)
- [MedSeqFT: Sequential Fine-tuning Foundation Models for 3D Medical Image Segmentation](https://mlsanity.com/paper/2509.06096/) (2025)
- [Beyond Weight Adaptation: Feature-Space Domain Injection for Cross-Modal Ship Re-Identification](https://mlsanity.com/paper/2512.20892/) (2025)
- [Parameters as Experts: Adapting Vision Models with Dynamic Parameter Routing](https://mlsanity.com/paper/2602.06862/) (2026)
- [Memory-Efficient Transfer Learning with Fading Side Networks via Masked Dual Path Distillation](https://mlsanity.com/paper/2604.09088/) (2026)
- [LSP-ST: Ladder Shape-Biased Side-Tuning for Robust Infrared Small Target Detection](https://mlsanity.com/paper/2504.14481/) (2025)
- [CrossEarth-Gate: Fisher-Guided Adaptive Tuning Engine for Efficient Adaptation of Cross-Domain Remote Sensing Semantic Segmentation](https://mlsanity.com/paper/2511.20302/) (2025)
- [MM-DETR: An Efficient Multimodal Detection Transformer with Mamba-Driven Dual-Granularity Fusion and Frequency-Aware Modality Adapters](https://mlsanity.com/paper/2512.00363/) (2025)
- [NAS-LoRA: Empowering Parameter-Efficient Fine-Tuning for Visual Foundation Models with Searchable Adaptation](https://mlsanity.com/paper/2512.03499/) (2025)
- [SCAFusion: A Multimodal 3D Detection Framework for Small Object Detection in Lunar Surface Exploration](https://mlsanity.com/paper/2512.22503/) (2025)
- [1%>100%: High-Efficiency Visual Adapter with Complex Linear Projection Optimization](https://mlsanity.com/paper/2602.10513/) (2026)
- [Fusion4CA: Boosting 3D Object Detection via Comprehensive Image Exploitation](https://mlsanity.com/paper/2603.05305/) (2026)
- [MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning](https://mlsanity.com/paper/2605.04058/) (2026)
- [Decoupled Motion Representation Learning for Moving Infrared Small Target Detection](https://mlsanity.com/paper/2606.15286/) (2026)
- [An Edge-aware Prompt-enhanced SAM for Ultrasound Image Segmentation](https://mlsanity.com/paper/2607.07240/) (2026)
- [Circuit Fine-Tuning for Compute-Efficient Transformer Adaptation](https://mlsanity.com/paper/2608.08336/) (2026)
- [PISA: A Pseudo-Individual Source-Domain Feature Adaptation Framework for Test-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2608.14142/) (2026)

## Abstract (arXiv)

Pre-training & fine-tuning can enhance the transferring efficiency and performance in visual tasks. Recent delta-tuning methods provide more options for visual classification tasks. Despite their success, existing visual delta-tuning art fails to exceed the upper limit of full fine-tuning on challenging tasks like object detection and segmentation. To find a competitive alternative to full fine-tuning, we propose the Multi-cognitive Visual Adapter (Mona) tuning, a novel adapter-based tuning method. First, we introduce multiple vision-friendly filters into the adapter to enhance its ability to process visual signals, while previous methods mainly rely on language-friendly linear filters. Second, we add the scaled normalization layer in the adapter to regulate the distribution of input features for visual filters. To fully demonstrate the practicality and generality of Mona, we conduct experiments on multiple representative visual tasks, including instance segmentation on COCO, semantic segmentation on ADE20K, object detection on Pascal VOC, oriented object detection on DOTA/STAR, and image classification on three common datasets. Exciting results illustrate that Mona surpasses full fine-tuning on all these tasks, and is the only delta-tuning method outperforming full fine-tuning on the above various tasks. For example, Mona achieves 1% performance gain on the COCO dataset compared to full fine-tuning. Comprehensive results suggest that Mona-tuning is more suitable for retaining and utilizing the capabilities of pre-trained models than full fine-tuning. The code will be released at https://github.com/Leiyi-Hu/mona.