# DTL: Disentangled Transfer Learning for Visual Recognition

arXiv: https://arxiv.org/abs/2312.07856 · HTML: https://mlsanity.com/paper/2312.07856/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 13 Dec 2023.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark](https://mlsanity.com/paper/1910.04867/) (2019)
- [Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning](https://mlsanity.com/paper/2210.08823/) (2022)
- [LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning](https://mlsanity.com/paper/2206.06522/) (2022)
- [FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer](https://mlsanity.com/paper/2212.03145/) (2022)
- [Multi-Label Self-Supervised Learning with Scene Images](https://mlsanity.com/paper/2308.03286/) (2023)

## Built on by (most cited first, 22 of 22)

- [Parameter-Efficient Fine-Tuning in Large Models: A Survey of Methodologies](https://mlsanity.com/paper/2410.19878/) (2024)
- [Parameter-Efficient Fine-Tuning for Foundation Models](https://mlsanity.com/paper/2501.13787/) (2025)
- [Self-Supervised Visual Preference Alignment](https://mlsanity.com/paper/2404.10501/) (2024)
- [Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark](https://mlsanity.com/paper/2402.02242/) (2024)
- [Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation](https://mlsanity.com/paper/2506.17307/) (2025)
- [Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference](https://mlsanity.com/paper/2405.14700/) (2024)
- [M2IST: Multi-Modal Interactive Side-Tuning for Efficient Referring Expression Comprehension](https://mlsanity.com/paper/2407.01131/) (2024)
- [PRO-VPT: Distribution-Adaptive Visual Prompt Tuning via Prompt Relocation](https://mlsanity.com/paper/2503.06901/) (2025)
- [GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers](https://mlsanity.com/paper/2506.11784/) (2025)
- [Tri-Efficient Transfer Learning for Point Cloud Videos](https://mlsanity.com/paper/2606.24175/) (2026)
- [SpectralX: Parameter-efficient Domain Generalization for Spectral Remote Sensing Foundation Models](https://mlsanity.com/paper/2508.01731/) (2025)
- [Multiple-Exit Tuning: Towards Inference-Efficient Adaptation for Vision Transformer](https://mlsanity.com/paper/2409.13999/) (2024)
- [Token Adaptation via Side Graph Convolution for Efficient Fine-tuning of 3D Point Cloud Transformers](https://mlsanity.com/paper/2502.14142/) (2025)
- [SHAPE : Self-Improved Visual Preference Alignment by Iteratively Generating Holistic Winner](https://mlsanity.com/paper/2503.04858/) (2025)
- [Efficient Multimodal Streaming Recommendation via Expandable Side Mixture-of-Experts](https://mlsanity.com/paper/2508.05993/) (2025)
- [Minimal Interaction Separated Tuning: A New Paradigm for Visual Adaptation](https://mlsanity.com/paper/2406.17559/) (2024)
- [Pre-training Everywhere: Parameter-Efficient Fine-Tuning for Medical Image Analysis via Target Parameter Pre-training](https://mlsanity.com/paper/2408.15011/) (2024)
- [KARST: Multi-Kernel Kronecker Adaptation with Re-Scaling Transmission for Visual Classification](https://mlsanity.com/paper/2502.06779/) (2025)
- [Optimizing Specific and Shared Parameters for Efficient Parameter Tuning](https://mlsanity.com/paper/2504.03450/) (2025)
- [OPFormer: Object Pose Estimation leveraging foundation model with geometric encoding](https://mlsanity.com/paper/2511.12614/) (2025)
- [Regularizing Subspace Redundancy of Low-Rank Adaptation](https://mlsanity.com/paper/2507.20745/) (2025)
- [PEFT-MuTS: A Multivariate Parameter-Efficient Fine-Tuning Framework for Remaining Useful Life Prediction based on Cross-domain Time Series Representation Model](https://mlsanity.com/paper/2601.22631/) (2026)

## Abstract (arXiv)

When pre-trained models become rapidly larger, the cost of fine-tuning on downstream tasks steadily increases, too. To economically fine-tune these models, parameter-efficient transfer learning (PETL) is proposed, which only tunes a tiny subset of trainable parameters to efficiently learn quality representations. However, current PETL methods are facing the dilemma that during training the GPU memory footprint is not effectively reduced as trainable parameters. PETL will likely fail, too, if the full fine-tuning encounters the out-of-GPU-memory issue. This phenomenon happens because trainable parameters from these methods are generally entangled with the backbone, such that a lot of intermediate states have to be stored in GPU memory for gradient propagation. To alleviate this problem, we introduce Disentangled Transfer Learning (DTL), which disentangles the trainable parameters from the backbone using a lightweight Compact Side Network (CSN). By progressively extracting task-specific information with a few low-rank linear mappings and appropriately adding the information back to the backbone, CSN effectively realizes knowledge transfer in various downstream tasks. We conducted extensive experiments to validate the effectiveness of our method. The proposed method not only reduces a large amount of GPU memory usage and trainable parameters, but also outperforms existing PETL methods by a significant margin in accuracy, achieving new state-of-the-art on several standard benchmarks. The code is available at https://github.com/heekhero/DTL.