mlsanityData to 14 Oct 2026

Noise-aware few-shot learning through bi-directional multi-view prompt alignment

arXiv 2603.11617 ↗First posted 12 Mar 2026cs.CVcited by 0

On the map: Multimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP

Abstract (arXiv)

Vision-language models offer strong few-shot capability through prompt tuning but remain vulnerable to noisy labels, which can corrupt prompts and degrade cross-modal alignment. Existing approaches struggle because they often lack the ability to model fine-grained semantic cues and to adaptively separate clean from noisy signals. To address these challenges, we propose NA-MVP, a framework for Noise-Aware few-shot learning through bi-directional Multi-View Prompt alignment. NA-MVP is built upon a key conceptual shift: robust prompt learning requires moving from global matching to region-aware alignment that explicitly distinguishes clean cues from noisy ones. To realize this, NA-MVP employs (1) multi-view prompts combined with unbalanced optimal transport to achieve fine-grained patch-to-prompt correspondence while suppressing unreliable regions; (2) a bi-directional prompt design that captures complementary clean-oriented and noise-aware cues, enabling the model to focus on stable semantics; and (3) an alignment-guided selective refinement strategy that uses optimal transport to correct only mislabeled samples while retaining reliable data. Experiments on synthetic and real-world noisy benchmarks demonstrate that NA-MVP consistently outperforms state-of-the-art baselines, confirming its effectiveness in enabling robust few-shot learning under noisy supervision.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 48 of its 68 references that are in the map. First posted on arXiv 12 Mar 2026.

Builds on

48 of 68 references.

Closest ancestors · 9

Same direction, newest first

  1. 2024NLPrompt: Noise-Label Prompt Learning for Vision-Language Models2 Dec
  2. 2024Vision-Language Models are Strong Noisy Label Detectors29 Sep
  3. 2023Why Is Prompt Tuning for Vision-Language Models Robust to Noisy Labels?22 Jul
  4. 2023Consistency-guided Prompt Learning for Vision-Language Models1 Jun
  5. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models15 Sep
  6. 2022Prompt-aligned Gradient for Prompt Tuning30 May
  7. 2022Prompt Distribution Learning6 May
  8. 2022Conditional Prompt Learning for Vision-Language Models10 Mar
  9. 2021Learning to Prompt for Vision-Language Models2 Sep

Other references · 39

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  3. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  4. 2013Describing Textures in the Wildcited by 2,125
  5. 2022CoCa: Contrastive Captioners are Image-Text Foundation Modelscited by 1,274
  6. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  7. 2022MaPLe: Multi-modal Prompt Learningcited by 687
  8. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 500
  9. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 328
  10. 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
  11. 2023Self-regulating Prompts: Foundational Model Adaptation without Forgettingcited by 272
  12. 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
27 more
  1. 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
  2. 2015Learning with a Wasserstein Losscited by 196
  3. 2017CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noisecited by 181
  4. 2021OTA: Optimal Transport Assignment for Object Detectioncited by 178
  5. 2021Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Losscited by 156
  6. 2017Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samplescited by 147
  7. 2023CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say Nocited by 130
  8. 2019Meta Label Correction for Noisy Label Learningcited by 108
  9. 2022DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotationscited by 102
  10. 2020Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptationcited by 87
  11. 2021FINE Samples for Learning with Noisy Labelscited by 82
  12. 2021Score-based Generative Neural Networks for Large-Scale Optimal Transportcited by 60
  13. 2021Open-set Label Noise Can Improve Robustness Against Inherent Label Noisecited by 59
  14. 2022Unified Optimal Transport Framework for Universal Domain Adaptationcited by 57
  15. 2022Learning with Neighbor Consistency for Noisy Labelscited by 55
  16. 2022Bayesian Prompt Learning for Image-Language Model Generalizationcited by 51
  17. 2023Generative Modeling through the Semi-dual Formulation of Unbalanced Optimal Transportcited by 41
  18. 2022Mitigating Memorization of Noisy Labels by Clipping the Model Predictioncited by 40
  19. 2019Robust Learning at Noisy Labeled Medical Images: Applied to Skin Lesion Classificationcited by 33
  20. 2022SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learningcited by 31
  21. 2022SELC: Self-Ensemble Label Correction Improves Learning with Noisy Labelscited by 24
  22. 2022Robust Medical Image Classification from Noisy Labeled Data with Global and Local Representation Guided Co-trainingcited by 21
  23. 2023CSOT: Curriculum and Structure-Aware Optimal Transport for Learning with Noisy Labelscited by 17
  24. 2017Two-stream Collaborative Learning with Spatial-Temporal Attention for Video Classificationcited by 16
  25. 2023Unbalanced Optimal Transport: A Unified Framework for Object Detectioncited by 15
  26. 2021Cascaded Robust Learning at Imperfect Labels for Chest X-ray Segmentationcited by 11
  27. 2022A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noisecited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Robust Prompt Tuning for Vision-Language Models with Mild Semantic Noise
  2. 2026Seeing is Believing: Robust Vision-Guided Cross-Modal Prompt Learning under Label Noise
  3. 2023Black Box Few-Shot Adaptation for Vision-Language models
  4. 2025TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks
  5. 2026Closed-Loop Bidirectional Prompting for Adversarial Robustness of Vision Language Models
  6. 2024PromptSync: Bridging Domain Gaps in Vision-Language Models through Class-Aware Prototype Alignment and Discrimination
  7. 2025Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation
  8. 2026ACPO: Counteracting Likelihood Displacement in Vision-Language Alignment with Asymmetric Constraints