Imagen de Portada

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:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Octic Vision Transformers: Quicker ViTs Through Equivariance
por: Nordström, David, et al.
Publicado: (2025)

STRAP-ViT: Segregated Tokens with Randomized -- Transformations for Defense against Adversarial Patches in ViTs
por: Chattopadhyay, Nandish, et al.
Publicado: (2026)

VIVID-Med: LLM-Supervised Structured Pretraining for Deployable Medical ViTs
por: Wang, Xiyao, et al.
Publicado: (2026)

Purrturbed but Stable: Human-Cat Invariant Representations Across CNNs, ViTs and Self-Supervised ViTs
por: Shah, Arya, et al.
Publicado: (2025)

CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs
por: Ramachandran, Akshat, et al.
Publicado: (2024)

ViTs are Everywhere: A Comprehensive Study Showcasing Vision Transformers in Different Domain
por: Mia, Md Sohag, et al.
Publicado: (2023)

Token Cropr: Faster ViTs for Quite a Few Tasks
por: Bergner, Benjamin, et al.
Publicado: (2024)

Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability
por: Liu, Jiani, et al.
Publicado: (2025)

I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization
por: Zhong, Yunshan, et al.
Publicado: (2023)

Colinearity Decay: Training Quantization-Friendly ViTs with Outlier Decay
por: Tong, Jin, et al.
Publicado: (2026)

AFIDAF: Alternating Fourier and Image Domain Adaptive Filters as an Efficient Alternative to Attention in ViTs
por: Zheng, Yunling, et al.
Publicado: (2024)

U-REPA: Aligning Diffusion U-Nets to ViTs
por: Tian, Yuchuan, et al.
Publicado: (2025)

Elastic ViTs from Pretrained Models without Retraining
por: Simoncini, Walter, et al.
Publicado: (2025)

Pretrained ViTs Yield Versatile Representations For Medical Images
por: Matsoukas, Christos, et al.
Publicado: (2023)

ViT-5: Vision Transformers for The Mid-2020s
por: Wang, Feng, et al.
Publicado: (2026)

Which Direction to Choose? An Analysis on the Representation Power of Self-Supervised ViTs in Downstream Tasks
por: Kaltampanidis, Yannis, et al.
Publicado: (2025)

EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation
por: Liu, Longfei, et al.
Publicado: (2026)

EA-ViT: Efficient Adaptation for Elastic Vision Transformer
por: Zhu, Chen, et al.
Publicado: (2025)

Exploring the Synergies of Hybrid CNNs and ViTs Architectures for Computer Vision: A survey
por: Yunusa, Haruna, et al.
Publicado: (2024)

LL-ViT: Edge Deployable Vision Transformers with Look Up Table Neurons
por: Nag, Shashank, et al.
Publicado: (2025)

Intriguing Frequency Interpretation of Adversarial Robustness for CNNs and ViTs
por: Chen, Lu, et al.
Publicado: (2025)

Training-Free Acceleration of ViTs with Delayed Spatial Merging
por: Heo, Jung Hwan, et al.
Publicado: (2023)

Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey
por: Siméoni, Oriane, et al.
Publicado: (2023)

Adapting Pretrained ViTs with Convolution Injector for Visuo-Motor Control
por: Hwang, Dongyoon, et al.
Publicado: (2024)

UniRefiner: Teaching Pre-trained ViTs to Self-Dispose Dross via Contrastive Register
por: Qiu, Congpei, et al.
Publicado: (2026)

ViT-DD: Multi-Task Vision Transformer for Semi-Supervised Driver Distraction Detection
por: Ma, Yunsheng, et al.
Publicado: (2022)

Parameter Efficient Fine-tuning of Self-supervised ViTs without Catastrophic Forgetting
por: Bafghi, Reza Akbarian, et al.
Publicado: (2024)

ACC-ViT : Atrous Convolution's Comeback in Vision Transformers
por: Ibtehaz, Nabil, et al.
Publicado: (2024)

PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference
por: Li, Ye, et al.
Publicado: (2024)

ConcatPlexer: Additional Dim1 Batching for Faster ViTs
por: Han, Donghoon, et al.
Publicado: (2023)

Frequency-Adaptive Discrete Cosine-ViT-ResNet Architecture for Sparse-Data Vision
por: Kang, Ziyue, et al.
Publicado: (2025)

ADFQ-ViT: Activation-Distribution-Friendly Post-Training Quantization for Vision Transformers
por: Jiang, Yanfeng, et al.
Publicado: (2024)

ViT-AdaLA: Adapting Vision Transformers with Linear Attention
por: Li, Yifan, et al.
Publicado: (2026)

IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformer
por: Ma, Xiaochen, et al.
Publicado: (2023)

Causality $\neq$ Decodability, and Vice Versa: Lessons from Interpreting Counting ViTs
por: Huang, Lianghuan, et al.
Publicado: (2025)

Communication Efficient Split Learning of ViTs with Attention-based Double Compression
por: Alvetreti, Federico, et al.
Publicado: (2025)

ViT-1.58b: Mobile Vision Transformers in the 1-bit Era
por: Yuan, Zhengqing, et al.
Publicado: (2024)

DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs
por: Kim, Donghyun, et al.
Publicado: (2024)

Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP
por: Balasubramanian, Sriram, et al.
Publicado: (2024)

HIRI-ViT: Scaling Vision Transformer with High Resolution Inputs
por: Yao, Ting, et al.
Publicado: (2024)