TAP-ViTs: Task-Adaptive Pruning for On-Device Deployment of Vision Transformers

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Zhibo, Zhang, Zuoyuan, Pang, Xiaoyi, Zhang, Qile, Hao, Xuanyi, Zhuo, Shuguo, Sun, Peng
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917185868267520
author Wang, Zhibo
Zhang, Zuoyuan
Pang, Xiaoyi
Zhang, Qile
Hao, Xuanyi
Zhuo, Shuguo
Sun, Peng
author_facet Wang, Zhibo
Zhang, Zuoyuan
Pang, Xiaoyi
Zhang, Qile
Hao, Xuanyi
Zhuo, Shuguo
Sun, Peng
contents Vision Transformers (ViTs) have demonstrated strong performance across a wide range of vision tasks, yet their substantial computational and memory demands hinder efficient deployment on resource-constrained mobile and edge devices. Pruning has emerged as a promising direction for reducing ViT complexity. However, existing approaches either (i) produce a single pruned model shared across all devices, ignoring device heterogeneity, or (ii) rely on fine-tuning with device-local data, which is often infeasible due to limited on-device resources and strict privacy constraints. As a result, current methods fall short of enabling task-customized ViT pruning in privacy-preserving mobile computing settings. This paper introduces TAP-ViTs, a novel task-adaptive pruning framework that generates device-specific pruned ViT models without requiring access to any raw local data. Specifically, to infer device-level task characteristics under privacy constraints, we propose a Gaussian Mixture Model (GMM)-based metric dataset construction mechanism. Each device fits a lightweight GMM to approximate its private data distribution and uploads only the GMM parameters. Using these parameters, the cloud selects distribution-consistent samples from public data to construct a task-representative metric dataset for each device. Based on this proxy dataset, we further develop a dual-granularity importance evaluation-based pruning strategy that jointly measures composite neuron importance and adaptive layer importance, enabling fine-grained, task-aware pruning tailored to each device's computational budget. Extensive experiments across multiple ViT backbones and datasets demonstrate that TAP-ViTs consistently outperforms state-of-the-art pruning methods under comparable compression ratios.
format Preprint
id arxiv_https___arxiv_org_abs_2601_02437
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TAP-ViTs: Task-Adaptive Pruning for On-Device Deployment of Vision Transformers
Wang, Zhibo
Zhang, Zuoyuan
Pang, Xiaoyi
Zhang, Qile
Hao, Xuanyi
Zhuo, Shuguo
Sun, Peng
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Vision Transformers (ViTs) have demonstrated strong performance across a wide range of vision tasks, yet their substantial computational and memory demands hinder efficient deployment on resource-constrained mobile and edge devices. Pruning has emerged as a promising direction for reducing ViT complexity. However, existing approaches either (i) produce a single pruned model shared across all devices, ignoring device heterogeneity, or (ii) rely on fine-tuning with device-local data, which is often infeasible due to limited on-device resources and strict privacy constraints. As a result, current methods fall short of enabling task-customized ViT pruning in privacy-preserving mobile computing settings. This paper introduces TAP-ViTs, a novel task-adaptive pruning framework that generates device-specific pruned ViT models without requiring access to any raw local data. Specifically, to infer device-level task characteristics under privacy constraints, we propose a Gaussian Mixture Model (GMM)-based metric dataset construction mechanism. Each device fits a lightweight GMM to approximate its private data distribution and uploads only the GMM parameters. Using these parameters, the cloud selects distribution-consistent samples from public data to construct a task-representative metric dataset for each device. Based on this proxy dataset, we further develop a dual-granularity importance evaluation-based pruning strategy that jointly measures composite neuron importance and adaptive layer importance, enabling fine-grained, task-aware pruning tailored to each device's computational budget. Extensive experiments across multiple ViT backbones and datasets demonstrate that TAP-ViTs consistently outperforms state-of-the-art pruning methods under comparable compression ratios.
title TAP-ViTs: Task-Adaptive Pruning for On-Device Deployment of Vision Transformers
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2601.02437