mlsanityData to 14 Oct 2026

Visual Variational Autoencoder Prompt Tuning

arXiv 2503.17650 ↗First posted 22 Mar 2025cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Parameter-efficient fine-tuning (PEFT) has emerged as a crucial approach for adapting large vision transformers to downstream tasks without the prohibitive computational costs of full fine-tuning. While existing visual prompt tuning (VPT) methods have made significant strides, they predominantly rely on static, domain-specific prompts that fail to capture the rich visual diversity within individual instances. This paper introduces V2APT (Visual Variational Autoencoder Prompt Tuning), a novel framework that generates dynamic, input-dependent prompts using a variational autoencoder architecture. By learning a latent representation of image-specific features and decoding them into customized prompts, V2APT adapts to the unique visual characteristics of each input. Extensive experiments on FGVC, HTA, and VTAB-1k benchmarks demonstrate that our approach consistently outperforms state-of-the-art PEFT methods. Notably, V2APT achieves +3.2% improvement over VPT-Deep on HTA, with an average performance gain of +2.0% across all three datasets.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 19 of its 32 references that are in the map. First posted on arXiv 22 Mar 2025.

Builds on

19 of 32 references.

References · 19

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2022Visual Prompt Tuningcited by 1,681
  5. 2022MaPLe: Multi-modal Prompt Learningcited by 687
  6. 2019A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmarkcited by 425
  7. 2017Wasserstein Auto-Encoderscited by 373
  8. 2022Unified Vision and Language Prompt Learningcited by 148
  9. 2021Variational Transformer Networks for Layout Generationcited by 88
  10. 2022Parameter-efficient Model Adaptation for Vision Transformerscited by 81
  11. 2022Revisiting Parameter-Efficient Tuning: Are We Really There Yet?cited by 76
  12. 2023E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuningcited by 70
7 more
  1. 2023Diversity-Aware Meta Visual Promptingcited by 58
  2. 2021How Well Do Sparse Imagenet Models Transfer?cited by 50
  3. 2024DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptationcited by 33
  4. 2024Visual Fourier Prompt Tuningcited by 30
  5. 2024OT-VP: Optimal Transport-guided Visual Prompting for Test-Time Adaptationcited by 17
  6. 2024Bayesian-guided Label Mapping for Visual Reprogrammingcited by 12
  7. 2025CAD-VAE: Leveraging Correlation-Aware Latents for Comprehensive Fair Disentanglementcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 5.

10 papers.

  1. 2025Visual Instance-aware Prompt Tuningcited by 29
  2. 2025FOCUS: Fused Observation of Channels for Unveiling Spectracited by 7
  3. 2025CTR-LoRA: Curvature-Aware and Trust-Region Guided Low-Rank Adaptation for Large Language Modelscited by 6
  4. 2026Prime Once, then Reprogram Locally: An Efficient Alternative to Black-Box Service Model Adaptationcited by 5
  5. 2025Self-Supervised Visual Prompting for Cross-Domain Road Damage Detectioncited by 3
  6. 2026DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detectioncited by 3
  7. 2026Visual Prompt-Agnostic Evolutioncited by 2
  8. 2026Layer-Specific Prompt Fusion Discovery via Differentiable Search in Vision Foundation Modelscited by 2
  9. 2025Boosting Active Learning with Knowledge Transfercited by 0
  10. 2026Adapting Vision Foundation Models with Cascaded Semanticscited by 0