Cover Image

Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Wangbo, Tang, Jiasheng, Han, Yizeng, Song, Yibing, Wang, Kai, Huang, Gao, Wang, Fan, You, Yang
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Dynamic Diffusion Transformer
by: Zhao, Wangbo, et al.
Published: (2024)

DyDiT++: Diffusion Transformers with Timestep and Spatial Dynamics for Efficient Visual Generation
by: Zhao, Wangbo, et al.
Published: (2025)

A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs
by: Zhao, Wangbo, et al.
Published: (2024)

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

RAPID^3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer
by: Zhao, Wangbo, et al.
Published: (2025)

Few-Step Distillation for Text-to-Image Generation: A Practical Guide
by: Pu, Yifan, et al.
Published: (2025)

ViT$^3$: Unlocking Test-Time Training in Vision
by: Han, Dongchen, et al.
Published: (2025)

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

Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference
by: You, Haoran, et al.
Published: (2022)

RepViT: Revisiting Mobile CNN From ViT Perspective
by: Wang, Ao, et al.
Published: (2023)

UniTTA: Unified Benchmark and Versatile Framework Towards Realistic Test-Time Adaptation
by: Du, Chaoqun, et al.
Published: (2024)

ViT-Lens: Towards Omni-modal Representations
by: Lei, Weixian, et al.
Published: (2023)

CAIT: Triple-Win Compression towards High Accuracy, Fast Inference, and Favorable Transferability For ViTs
by: Wang, Ao, et al.
Published: (2023)

SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning
by: Du, Chaoqun, et al.
Published: (2024)

Accelerating ViT Inference on FPGA through Static and Dynamic Pruning
by: Parikh, Dhruv, et al.
Published: (2024)

BlockVid: Block Diffusion for High-Quality and Consistent Minute-Long Video Generation
by: Zhang, Zeyu, et al.
Published: (2025)

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

Exploiting Lightweight Hierarchical ViT and Dynamic Framework for Efficient Visual Tracking
by: Kang, Ben, et al.
Published: (2025)

Mobile U-ViT: Revisiting large kernel and U-shaped ViT for efficient medical image segmentation
by: Tang, Fenghe, et al.
Published: (2025)

DyFADet: Dynamic Feature Aggregation for Temporal Action Detection
by: Yang, Le, et al.
Published: (2024)

Rethinking Random Masking in Self-Distillation on ViT
by: Seong, Jihyeon, et al.
Published: (2025)

Parameter-Efficient Subspace Decoupling ViT for Mitigating Multi-Task Negative Transfer in Histological Scoring
by: Huang, Youhan, et al.
Published: (2026)

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

One-Shot Multilingual Font Generation Via ViT
by: Wang, Zhiheng, et al.
Published: (2024)

Multiple-Exit Tuning: Towards Inference-Efficient Adaptation for Vision Transformer
by: Liu, Zheng, et al.
Published: (2024)

Deeper Inside Deep ViT
by: Hong, Sungrae
Published: (2025)

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

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

Latency-aware Unified Dynamic Networks for Efficient Image Recognition
by: Han, Yizeng, et al.
Published: (2023)

CNN and ViT Efficiency Study on Tiny ImageNet and DermaMNIST Datasets
by: Amangeldi, Aidar, et al.
Published: (2025)

Let ViT Speak: Generative Language-Image Pre-training
by: Fang, Yan, et al.
Published: (2026)

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

Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection
by: Zhang, Jiangning, et al.
Published: (2023)

ViTCAE: ViT-based Class-conditioned Autoencoder
by: Jebraeeli, Vahid, et al.
Published: (2025)

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

When CNN Meet with ViT: Towards Semi-Supervised Learning for Multi-Class Medical Image Semantic Segmentation
by: Wang, Ziyang, et al.
Published: (2022)

HydraViT: Stacking Heads for a Scalable ViT
by: Haberer, Janek, et al.
Published: (2024)

EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training
by: Wang, Yulin, et al.
Published: (2024)

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

Modulating CNN Features with Pre-Trained ViT Representations for Open-Vocabulary Object Detection
by: Gao, Xiangyu, et al.
Published: (2025)