Split Adaptation for Pre-trained Vision Transformers

• URL: http://arxiv.org/abs/2503.00441v1
• Date: Sat, 01 Mar 2025 10:38:53 GMT
• Title: Split Adaptation for Pre-trained Vision Transformers
• Authors: Lixu Wang, Bingqi Shang, Yi Li, Payal Mohapatra, Wei Dong, Xiao Wang, Qi Zhu,
• Abstract summary: We propose a novel split adaptation (SA) method that enables effective downstream adaptation while protecting data and models.<n>Unlike regular SL, SA replaces parameters with low-bit quantized values, preventing direct exposure of the model.<n>SA incorporates data-level and model-level out-of-distribution enhancements to mitigate noise injection's impact on adaptation performance.
• Score: 17.25680016753443
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision Transformers (ViTs), extensively pre-trained on large-scale datasets, have become essential to foundation models, allowing excellent performance on diverse downstream tasks with minimal adaptation. Consequently, there is growing interest in adapting pre-trained ViTs across various fields, including privacy-sensitive domains where clients are often reluctant to share their data. Existing adaptation methods typically require direct data access, rendering them infeasible under these constraints. A straightforward solution may be sending the pre-trained ViT to clients for local adaptation, which poses issues of model intellectual property protection and incurs heavy client computation overhead. To address these issues, we propose a novel split adaptation (SA) method that enables effective downstream adaptation while protecting data and models. SA, inspired by split learning (SL), segments the pre-trained ViT into a frontend and a backend, with only the frontend shared with the client for data representation extraction. But unlike regular SL, SA replaces frontend parameters with low-bit quantized values, preventing direct exposure of the model. SA allows the client to add bi-level noise to the frontend and the extracted data representations, ensuring data protection. Accordingly, SA incorporates data-level and model-level out-of-distribution enhancements to mitigate noise injection's impact on adaptation performance. Our SA focuses on the challenging few-shot adaptation and adopts patch retrieval augmentation for overfitting alleviation. Extensive experiments on multiple datasets validate SA's superiority over state-of-the-art methods and demonstrate its defense against advanced data reconstruction attacks while preventing model leakage with minimal computation cost on the client side. The source codes can be found at https://github.com/conditionWang/Split_Adaptation.

Related papers

• FedCTTA: A Collaborative Approach to Continual Test-Time Adaptation in Federated Learning [0.956984177686999]
  Federated Learning (FL) enables collaborative model training across distributed clients without sharing raw data.<n>FL models often suffer performance degradation due to distribution shifts between training and deployment.<n>We propose Federated Continual Test-Time Adaptation (FedCTTA), a privacy-preserving and computationally efficient framework for federated adaptation.
  arXiv  Detail & Related papers  (2025-05-19T18:29:51Z)
• Optimal Transport-Guided Source-Free Adaptation for Face Anti-Spoofing [58.56017169759816]
  We introduce a novel method in which the face anti-spoofing model can be adapted by the client itself to a target domain at test time. Specifically, we develop a prototype-based base model and an optimal transport-guided adaptor. In cross-domain and cross-attack settings, compared with recent methods, our method achieves average relative improvements of 19.17% in HTER and 8.58% in AUC.
  arXiv  Detail & Related papers  (2025-03-29T06:10:34Z)
• FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors [50.131271229165165]
  Federated Learning (FL) has emerged as a promising framework for distributed machine learning. Data heterogeneity resulting from differences across user behaviors, preferences, and device characteristics poses a significant challenge for federated learning. We propose Adaptive Weight Aggregation (FedAWA), a novel method that adaptively adjusts aggregation weights based on client vectors during the learning process.
  arXiv  Detail & Related papers  (2025-03-20T04:49:40Z)
• PeFAD: A Parameter-Efficient Federated Framework for Time Series Anomaly Detection [51.20479454379662]
  We propose a. Federated Anomaly Detection framework named PeFAD with the increasing privacy concerns. We conduct extensive evaluations on four real datasets, where PeFAD outperforms existing state-of-the-art baselines by up to 28.74%.
  arXiv  Detail & Related papers  (2024-06-04T13:51:08Z)
• Enhancing Accuracy-Privacy Trade-off in Differentially Private Split Learning [2.2676798389997863]
  Split learning (SL) aims to protect user data privacy by distributing deep models between client-server and keeping private data locally. Recently proposed model inversion attacks can recover the original data from the smashed data. A strategy is to adopt differential privacy (DP), which involves safeguarding the smashed data at the expense of some accuracy loss.
  arXiv  Detail & Related papers  (2023-10-22T22:45:13Z)
• Informative Data Mining for One-Shot Cross-Domain Semantic Segmentation [84.82153655786183]
  We propose a novel framework called Informative Data Mining (IDM) to enable efficient one-shot domain adaptation for semantic segmentation. IDM provides an uncertainty-based selection criterion to identify the most informative samples, which facilitates quick adaptation and reduces redundant training. Our approach outperforms existing methods and achieves a new state-of-the-art one-shot performance of 56.7%/55.4% on the GTA5/SYNTHIA to Cityscapes adaptation tasks.
  arXiv  Detail & Related papers  (2023-09-25T15:56:01Z)
• Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer [54.32283739486781]
  We present a textbfForgery-aware textbfAdaptive textbfVision textbfTransformer (FA-ViT) under the adaptive learning paradigm. FA-ViT achieves 93.83% and 78.32% AUC scores on Celeb-DF and DFDC datasets in the cross-dataset evaluation.
  arXiv  Detail & Related papers  (2023-09-20T06:51:11Z)
• A More Secure Split: Enhancing the Security of Privacy-Preserving Split Learning [2.853180143237022]
  Split learning (SL) is a new collaborative learning technique that allows participants to train machine learning models without the client sharing raw data. Previous works demonstrated that reconstructing Activation Maps (AMs) could result in privacy leakage of client data. In this paper, we improve upon previous works by constructing a protocol based on U-shaped SL that can operate on homomorphically encrypted data.
  arXiv  Detail & Related papers  (2023-09-15T18:39:30Z)
• Split Ways: Privacy-Preserving Training of Encrypted Data Using Split Learning [6.916134299626706]
  Split Learning (SL) is a new collaborative learning technique that allows participants to train machine learning models without the client sharing raw data. Previous works demonstrated that reconstructing activation maps could result in privacy leakage of client data. In this paper, we improve upon previous works by constructing a protocol based on U-shaped SL that can operate on homomorphically encrypted data.
  arXiv  Detail & Related papers  (2023-01-20T19:26:51Z)
• CAFA: Class-Aware Feature Alignment for Test-Time Adaptation [50.26963784271912]
  Test-time adaptation (TTA) aims to address this challenge by adapting a model to unlabeled data at test time. We propose a simple yet effective feature alignment loss, termed as Class-Aware Feature Alignment (CAFA), which simultaneously encourages a model to learn target representations in a class-discriminative manner.
  arXiv  Detail & Related papers  (2022-06-01T03:02:07Z)
• Self-Supervised Pre-Training for Transformer-Based Person Re-Identification [54.55281692768765]
  Transformer-based supervised pre-training achieves great performance in person re-identification (ReID) Due to the domain gap between ImageNet and ReID datasets, it usually needs a larger pre-training dataset to boost the performance. This work aims to mitigate the gap between the pre-training and ReID datasets from the perspective of data and model structure.
  arXiv  Detail & Related papers  (2021-11-23T18:59:08Z)

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.