Adapting Vision Foundation Models with Cascaded Semantics

• URL: http://arxiv.org/abs/2608.05393v1
• Date: Wed, 05 Aug 2026 20:23:40 GMT
• Title: Adapting Vision Foundation Models with Cascaded Semantics
• Abstract summary: Visual prompt tuning (VPT) adapts pre-trained vision transformers (ViTs) by updating a small set of additional prompt parameters.<n>We address this gap by injecting two complementary semantic priors into VPT.<n>We propose a cascaded scheme that integrates both priors throughout ViT adaptation.
• Score: 41.09567727920525
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Prompt tuning, a leading parameter-efficient adaptation paradigm in NLP, has recently been extended to computer vision. Visual prompt tuning (VPT) adapts pre-trained vision transformers (ViTs) by updating a small set of additional prompt parameters. However, existing visual prompts are randomly initialized and do not exploit prior knowledge, such as instructions in NLP. We address this gap by injecting two complementary semantic priors into VPT. Fundamental image priors, including color, texture, and shape, are extracted with classical hand-crafted operators and injected into the input space, while self-attention maps provide instance-aware semantics in the feature space. We further propose a cascaded scheme that integrates both priors throughout ViT adaptation. Experiments on 34 challenging image classification datasets demonstrate superior downstream adaptation while tuning only 0.74% of ViT parameters. Project page: https://xixiaouab.github.io/Cascaded-Semantics/.

Related papers

• Visual Variational Autoencoder Prompt Tuning [20.387933505896388]
  This paper introduces V$2$APT (Visual Variational Autoencoder Prompt Tuning), a novel framework that generates dynamic, input-dependent prompts.<n>Experiments on FGVC, HTA, and VTAB-1k benchmarks demonstrate that our approach consistently outperforms state-of-the-art PEFT methods.
  arXiv  Detail & Related papers  (2025-03-22T04:59:51Z)
• Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference [14.030836300221756]
  textbfSparse-Tuning is a novel PEFT method that accounts for the information redundancy in images and videos. Sparse-Tuning minimizes the quantity of tokens processed at each layer, leading to a quadratic reduction in computational and memory overhead. Our results show that our Sparse-Tuning reduces GFLOPs to textbf62%-70% of the original ViT-B while achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-05-23T15:34:53Z)
• Denoising Vision Transformers [43.03068202384091]
  We propose a two-stage denoising approach, termed Denoising Vision Transformers (DVT) In the first stage, we separate the clean features from those contaminated by positional artifacts by enforcing cross-view feature consistency with neural fields on a per-image basis. In the second stage, we train a lightweight transformer block to predict clean features from raw ViT outputs, leveraging the derived estimates of the clean features as supervision.
  arXiv  Detail & Related papers  (2024-01-05T18:59:52Z)
• p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models [10.713680139939354]
  Vision-Language models (VLMs) pre-trained on large corpora have demonstrated notable success across a range of downstream tasks. PETL has garnered attention as a viable alternative to full fine-tuning. We propose a new adapter architecture, $p$-adapter, which employs $p$-Laplacian message passing in Graph Neural Networks (GNNs)
  arXiv  Detail & Related papers  (2023-12-17T05:30:35Z)
• PriViT: Vision Transformers for Fast Private Inference [55.36478271911595]
  Vision Transformer (ViT) architecture has emerged as the backbone of choice for state-of-the-art deep models for computer vision applications. ViTs are ill-suited for private inference using secure multi-party protocols, due to the large number of non-polynomial operations. We propose PriViT, an algorithm to selectively " Taylorize" nonlinearities in ViTs while maintaining their prediction accuracy.
  arXiv  Detail & Related papers  (2023-10-06T21:45:05Z)
• TRIPS: Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection [61.0662744915659]
  We propose an efficient vision-and-language pre-training model with textbfText-textbfRelevant textbfImage textbfPatch textbfSelection, namely TRIPS.<n> TRIPS reduces the visual sequence progressively with a text-guided patch-selection layer in the visual backbone for efficient training and inference.
  arXiv  Detail & Related papers  (2023-05-08T05:53:30Z)
• Exploring Efficient Few-shot Adaptation for Vision Transformers [70.91692521825405]
  We propose a novel efficient Transformer Tuning (eTT) method that facilitates finetuning ViTs in the Few-shot Learning tasks. Key novelties come from the newly presented Attentive Prefix Tuning (APT) and Domain Residual Adapter (DRA) We conduct extensive experiments to show the efficacy of our model.
  arXiv  Detail & Related papers  (2023-01-06T08:42:05Z)
• Pro-tuning: Unified Prompt Tuning for Vision Tasks [133.12978197265596]
  Fine-tuning is the de-facto approach to leverage pre-trained vision models to perform downstream tasks. In this work, we propose parameter-efficient Prompt tuning (Pro-tuning) to adapt frozen vision models to various downstream vision tasks.
  arXiv  Detail & Related papers  (2022-07-28T21:09:31Z)
• AdaViT: Adaptive Tokens for Efficient Vision Transformer [91.88404546243113]
  We introduce AdaViT, a method that adaptively adjusts the inference cost of vision transformer (ViT) for images of different complexity. AdaViT achieves this by automatically reducing the number of tokens in vision transformers that are processed in the network as inference proceeds.
  arXiv  Detail & Related papers  (2021-12-14T18:56:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.