# DePT: Decoupled Prompt Tuning

arXiv: https://arxiv.org/abs/2309.07439 · HTML: https://mlsanity.com/paper/2309.07439/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 61 references that are in the map.
- First posted on arXiv 14 Sep 2023.

## Builds on (most cited first, 30 of 39)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields](https://mlsanity.com/paper/2112.05139/) (2021)
- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [Parameter-Efficient Transfer Learning with Diff Pruning](https://mlsanity.com/paper/2012.07463/) (2020)
- [Prompt-aligned Gradient for Prompt Tuning](https://mlsanity.com/paper/2205.14865/) (2022)
- [Visual-Language Prompt Tuning with Knowledge-guided Context Optimization](https://mlsanity.com/paper/2303.13283/) (2023)
- [X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval](https://mlsanity.com/paper/2207.07285/) (2022)
- [Self-regulating Prompts: Foundational Model Adaptation without Forgetting](https://mlsanity.com/paper/2307.06948/) (2023)
- [Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss](https://mlsanity.com/paper/2109.04290/) (2021)

## Built on by (most cited first, 30 of 58)

- [TCP:Textual-based Class-aware Prompt tuning for Visual-Language Model](https://mlsanity.com/paper/2311.18231/) (2023)
- [Parameter-Efficient Fine-Tuning for Foundation Models](https://mlsanity.com/paper/2501.13787/) (2025)
- [RandLoRA: Full-rank parameter-efficient fine-tuning of large models](https://mlsanity.com/paper/2502.00987/) (2025)
- [AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation](https://mlsanity.com/paper/2407.04603/) (2024)
- [Advancing Textual Prompt Learning with Anchored Attributes](https://mlsanity.com/paper/2412.09442/) (2024)
- [Cascade Prompt Learning for Vision-Language Model Adaptation](https://mlsanity.com/paper/2409.17805/) (2024)
- [Deep Correlated Prompting for Visual Recognition with Missing Modalities](https://mlsanity.com/paper/2410.06558/) (2024)
- [DPC: Dual-Prompt Collaboration for Tuning Vision-Language Models](https://mlsanity.com/paper/2503.13443/) (2025)
- [Reliable Few-shot Learning under Dual Noises](https://mlsanity.com/paper/2506.16330/) (2025)
- [Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model](https://mlsanity.com/paper/2503.04543/) (2025)
- [From Channel Bias to Feature Redundancy: Uncovering the "Less is More" Principle in Few-Shot Learning](https://mlsanity.com/paper/2310.03843/) (2023)
- [Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves](https://mlsanity.com/paper/2412.11509/) (2024)
- [Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptation](https://mlsanity.com/paper/2506.23271/) (2025)
- [Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models](https://mlsanity.com/paper/2410.02681/) (2024)
- [A Closer Look at Conditional Prompt Tuning for Vision-Language Models](https://mlsanity.com/paper/2506.23856/) (2025)
- [Synergistic Prompting for Robust Visual Recognition with Missing Modalities](https://mlsanity.com/paper/2507.07802/) (2025)
- [Generalizing vision-language models to novel domains: A comprehensive survey](https://mlsanity.com/paper/2506.18504/) (2025)
- [ProS: Prompting-to-simulate Generalized knowledge for Universal Cross-Domain Retrieval](https://mlsanity.com/paper/2312.12478/) (2023)
- [Referring Expression Comprehension for Small Objects](https://mlsanity.com/paper/2510.03701/) (2025)
- [Medical Knowledge Intervention Prompt Tuning for Medical Image Classification](https://mlsanity.com/paper/2511.12639/) (2025)
- [Few-Shot Image Quality Assessment via Adaptation of Vision-Language Models](https://mlsanity.com/paper/2409.05381/) (2024)
- [FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models](https://mlsanity.com/paper/2504.20860/) (2025)
- [MetaTT: A Global Tensor-Train Adapter for Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2506.09105/) (2025)
- [MoRA: Missing Modality Low-Rank Adaptation for Visual Recognition](https://mlsanity.com/paper/2511.06225/) (2025)
- [Learning Generalizable Prompt for CLIP with Class Similarity Knowledge](https://mlsanity.com/paper/2502.11969/) (2025)
- [Generalizable Prompt Learning of CLIP: A Brief Overview](https://mlsanity.com/paper/2503.01263/) (2025)
- [MAO: Efficient Model-Agnostic Optimization of Prompt Tuning for Vision-Language Models](https://mlsanity.com/paper/2503.18160/) (2025)
- [Diff-Prompt: Diffusion-Driven Prompt Generator with Mask Supervision](https://mlsanity.com/paper/2504.21423/) (2025)
- [GLAD: Generalizable Tuning for Vision-Language Models](https://mlsanity.com/paper/2507.13089/) (2025)
- [OV-COAST: Cost Aggregation with Optimal Transport for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2506.03706/) (2025)

## Abstract (arXiv)

This work breaks through the Base-New Tradeoff (BNT)dilemma in prompt tuning, i.e., the better the tuned model generalizes to the base (or target) task, the worse it generalizes to new tasks, and vice versa. Specifically, through an in-depth analysis of the learned features of the base and new tasks, we observe that the BNT stems from a channel bias issue, i.e., the vast majority of feature channels are occupied by base-specific knowledge, resulting in the collapse of taskshared knowledge important to new tasks. To address this, we propose the Decoupled Prompt Tuning (DePT) framework, which decouples base-specific knowledge from feature channels into an isolated feature space during prompt tuning, so as to maximally preserve task-shared knowledge in the original feature space for achieving better zero-shot generalization on new tasks. Importantly, our DePT is orthogonal to existing prompt tuning methods, hence it can improve all of them. Extensive experiments on 11 datasets show the strong flexibility and effectiveness of DePT. Our code and pretrained models are available at https://github.com/Koorye/DePT.