mlsanityData to 14 Oct 2026

DePT: Decoupled Prompt Tuning

arXiv 2309.07439 ↗First posted 14 Sep 2023cs.CVcited by 58

Not on the map. Why?

Cited by 34 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

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.

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

39 of 61 references.

References · 39

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  4. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  5. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  6. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,222
  7. 2013Describing Textures in the Wildcited by 2,125
  8. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  9. 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
  10. 2022Visual Prompt Tuningcited by 1,681
  11. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,619
  12. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,515
27 more
  1. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,496
  2. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,433
  3. 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,245
  4. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,230
  5. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,026
  6. 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,013
  7. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 991
  8. 2022MaPLe: Multi-modal Prompt Learningcited by 687
  9. 2021Extract Free Dense Labels from CLIPcited by 583
  10. 2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 532
  11. 2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 370
  12. 2022Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classificationcited by 362
  13. 2020Parameter-Efficient Transfer Learning with Diff Pruningcited by 352
  14. 2022Prompt-aligned Gradient for Prompt Tuningcited by 341
  15. 2023Visual-Language Prompt Tuning with Knowledge-guided Context Optimizationcited by 308
  16. 2022X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrievalcited by 280
  17. 2023Self-regulating Prompts: Foundational Model Adaptation without Forgettingcited by 272
  18. 2021Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Losscited by 116
  19. 2021WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Trainingcited by 84
  20. 2022PLOT: Prompt Learning with Optimal Transport for Vision-Language Modelscited by 64
  21. 2023Diversity-Aware Meta Visual Promptingcited by 58
  22. 2023StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learningcited by 53
  23. 2021Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Datacited by 48
  24. 2023A Closer Look at Few-shot Classification Againcited by 46
  25. 2022Learning to Decompose Visual Features with Latent Textual Promptscited by 28
  26. 2023From Global to Local: Multi-scale Out-of-distribution Detectioncited by 18
  27. 2023DETA: Denoised Task Adaptation for Few-Shot Learningcited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 11; 2025: 38; 2026: 6.

58 papers.

Sort:

By area:

  1. 2023TCP:Textual-based Class-aware Prompt tuning for Visual-Language Modelcited by 76
  2. 2025Parameter-Efficient Fine-Tuning for Foundation Modelscited by 45
  3. 2025RandLoRA: Full-rank parameter-efficient fine-tuning of large modelscited by 35
  4. 2024AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportationcited by 28
  5. 2024Advancing Textual Prompt Learning with Anchored Attributescited by 20
  6. 2024Cascade Prompt Learning for Vision-Language Model Adaptationcited by 19
  7. 2024Deep Correlated Prompting for Visual Recognition with Missing Modalitiescited by 18
  8. 2025DPC: Dual-Prompt Collaboration for Tuning Vision-Language Modelscited by 18
  9. 2025Reliable Few-shot Learning under Dual Noisescited by 17
  10. 2025Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Modelcited by 16
  11. 2023From Channel Bias to Feature Redundancy: Uncovering the "Less is More" Principle in Few-Shot Learningcited by 10
  12. 2024Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselvescited by 10
38 more
  1. 2025Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptationcited by 10
  2. 2024Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Modelscited by 9
  3. 2025A Closer Look at Conditional Prompt Tuning for Vision-Language Modelscited by 8
  4. 2025Synergistic Prompting for Robust Visual Recognition with Missing Modalitiescited by 8
  5. 2025Generalizing vision-language models to novel domains: A comprehensive surveycited by 7
  6. 2023ProS: Prompting-to-simulate Generalized knowledge for Universal Cross-Domain Retrievalcited by 6
  7. 2025Referring Expression Comprehension for Small Objectscited by 6
  8. 2025Medical Knowledge Intervention Prompt Tuning for Medical Image Classificationcited by 5
  9. 2024Few-Shot Image Quality Assessment via Adaptation of Vision-Language Modelscited by 4
  10. 2025FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Modelscited by 4
  11. 2025MetaTT: A Global Tensor-Train Adapter for Parameter-Efficient Fine-Tuningcited by 4
  12. 2025MoRA: Missing Modality Low-Rank Adaptation for Visual Recognitioncited by 4
  13. 2025Learning Generalizable Prompt for CLIP with Class Similarity Knowledgecited by 3
  14. 2025Generalizable Prompt Learning of CLIP: A Brief Overviewcited by 3
  15. 2025MAO: Efficient Model-Agnostic Optimization of Prompt Tuning for Vision-Language Modelscited by 3
  16. 2025Diff-Prompt: Diffusion-Driven Prompt Generator with Mask Supervisioncited by 3
  17. 2025GLAD: Generalizable Tuning for Vision-Language Modelscited by 3
  18. 2025OV-COAST: Cost Aggregation with Optimal Transport for Open-Vocabulary Semantic Segmentationcited by 2
  19. 2025Multi-modal Mutual-Guidance Conditional Prompt Learning for Vision-Language Modelscited by 2
  20. 2025One Last Attention for Your Vision-Language Modelcited by 2
  21. 2025Dual-branch Prompting for Multimodal Machine Translationcited by 2
  22. 2025MoLT: Mixture of Layer-Wise Tokens for Efficient Audio-Visual Learningcited by 2
  23. 2025Geometric Prior-Guided Federated Prompt Calibrationcited by 2
  24. 2024CoAPT: Context Attribute words for Prompt Tuningcited by 1
  25. 2024Craft: Cross-modal Aligned Features Improve Robustness of Prompt Tuningcited by 1
  26. 2024LPT: Less-overfitting Prompt Tuning for Vision-Language Modelcited by 1
  27. 2024MoPD: Mixture-of-Prompts Distillation for Vision-Language Modelscited by 1
  28. 2025Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimizationcited by 1
  29. 2025Alternating Training-based Label Smoothing Enhances Prompt Generalizationcited by 1
  30. 2025Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learningcited by 1
  31. 2025AnchorOPT: Towards Optimizing Dynamic Anchors for Adaptive Prompt Learningcited by 1
  32. 2026FVG-PT: Adaptive Foreground View-Guided Prompt Tuning for Vision-Language Modelscited by 1
  33. 2025InPK: Infusing Prior Knowledge into Prompt for Vision-Language Modelscited by 0
  34. 2025DPL: Decoupled Prototype Learning for Enhancing Robustness of Vision-Language Transformers to Missing Modalitiescited by 0
  35. 2025PCoreSet: Effective Active Learning through Knowledge Distillation from Vision-Language Modelscited by 0
  36. 2025AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectivescited by 0
  37. 2025Exploiting Vision Language Model for Training-Free 3D Point Cloud OOD Detection via Graph Score Propagationcited by 0
  38. 2025Integrated Structural Prompt Learning for Vision-Language Modelscited by 0

50 most cited of 58 All 58 (JSON)