Copertina

Dynamic Granularity Matters: Rethinking Vision Transformers Beyond Fixed Patch Splitting

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yu, Qiyang, Fang, Yu, Li, Tianrui, Cao, Xuemei, Chen, Yan, Li, Jianghao, Min, Fan
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Granular Computing-driven SAM: From Coarse-to-Fine Guidance for Prompt-Free Segmentation
di: Yu, Qiyang, et al.
Pubblicazione: (2025)

Visual-Word Tokenizer: Beyond Fixed Sets of Tokens in Vision Transformers
di: Gee, Leonidas, et al.
Pubblicazione: (2024)

Brain-Inspired Stepwise Patch Merging for Vision Transformers
di: Yu, Yonghao, et al.
Pubblicazione: (2024)

Dynamic Topology Awareness: Breaking the Granularity Rigidity in Vision-Language Navigation
di: Peng, Jiankun, et al.
Pubblicazione: (2026)

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads
di: Li, Yifan, et al.
Pubblicazione: (2025)

Dynamic Texture Transfer using PatchMatch and Transformers
di: Pu, Guo, et al.
Pubblicazione: (2024)

MGRQ: Post-Training Quantization For Vision Transformer With Mixed Granularity Reconstruction
di: Yang, Lianwei, et al.
Pubblicazione: (2024)

MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer
di: Cao, Jianjian, et al.
Pubblicazione: (2024)

Semantic Graph Consistency: Going Beyond Patches for Regularizing Self-Supervised Vision Transformers
di: Devaguptapu, Chaitanya, et al.
Pubblicazione: (2024)

Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches
di: Yu, Qing, et al.
Pubblicazione: (2024)

Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustness
di: Alonso, Pedro, et al.
Pubblicazione: (2026)

Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications
di: Xiong, Yuwen, et al.
Pubblicazione: (2024)

All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning
di: Yang, Zheng, et al.
Pubblicazione: (2025)

Temporal Prompting Matters: Rethinking Referring Video Object Segmentation
di: Lin, Ci-Siang, et al.
Pubblicazione: (2025)

Retina Vision Transformer (RetinaViT): Introducing Scaled Patches into Vision Transformers
di: Shu, Yuyang, et al.
Pubblicazione: (2024)

Context-Aware Token Selection and Packing for Enhanced Vision Transformer
di: Zhang, Tianyi, et al.
Pubblicazione: (2024)

A Timely Survey on Vision Transformer for Deepfake Detection
di: Wang, Zhikan, et al.
Pubblicazione: (2024)

Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer
di: Wu, Junyi, et al.
Pubblicazione: (2024)

Beyond Blanket Masking: Examining Granularity for Privacy Protection in Images Captured by Blind and Low Vision Users
di: Murrugarra-LLerena, Jeffri, et al.
Pubblicazione: (2025)

A New Perspective on Privacy Protection in Federated Learning with Granular-Ball Computing
di: Lai, Guannan, et al.
Pubblicazione: (2025)

Rethinking Occlusion in FER: A Semantic-Aware Perspective and Go Beyond
di: Zhai, Huiyu, et al.
Pubblicazione: (2025)

Split Adaptation for Pre-trained Vision Transformers
di: Wang, Lixu, et al.
Pubblicazione: (2025)

Rethinking Scanning Strategies with Vision Mamba in Semantic Segmentation of Remote Sensing Imagery: An Experimental Study
di: Zhu, Qinfeng, et al.
Pubblicazione: (2024)

Entropy Guided Dynamic Patch Segmentation for Time Series Transformers
di: Abeywickrama, Sachith, et al.
Pubblicazione: (2025)

UltraImage: Rethinking Resolution Extrapolation in Image Diffusion Transformers
di: Zhao, Min, et al.
Pubblicazione: (2025)

Hi-ResNet: Edge Detail Enhancement for High-Resolution Remote Sensing Segmentation
di: Chen, Yuxia, et al.
Pubblicazione: (2023)

Rethinking Patch Dependence for Masked Autoencoders
di: Fu, Letian, et al.
Pubblicazione: (2024)

Revisiting Audio-Visual Segmentation with Vision-Centric Transformer
di: Huang, Shaofei, et al.
Pubblicazione: (2025)

HiAP: A Multi-Granular Stochastic Auto-Pruning Framework for Vision Transformers
di: Li, Andy, et al.
Pubblicazione: (2026)

Stratify or Die: Rethinking Data Splits in Image Segmentation
di: Jami, Naga Venkata Sai Jitin, et al.
Pubblicazione: (2025)

From Per-Image Low-Rank to Encoding Mismatch: Rethinking Feature Distillation in Vision Transformers
di: Tian, Huiyuan, et al.
Pubblicazione: (2025)

Multi-Granularity Language-Guided Training for Multi-Object Tracking
di: Li, Yuhao, et al.
Pubblicazione: (2024)

Rethinking Vision Transformer Depth via Structural Reparameterization
di: Zhou, Chengwei, et al.
Pubblicazione: (2025)

Patch-based Selection and Refinement for Early Object Detection
di: Zhang, Tianyi, et al.
Pubblicazione: (2023)

Rethinking Query-based Transformer for Continual Image Segmentation
di: Zhu, Yuchen, et al.
Pubblicazione: (2025)

Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs
di: Su, Yongyi, et al.
Pubblicazione: (2025)

Generalized Correspondence Matching via Flexible Hierarchical Refinement and Patch Descriptor Distillation
di: Han, Yu, et al.
Pubblicazione: (2024)

Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?
di: Fu, Yonggan, et al.
Pubblicazione: (2022)

Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models
di: Yin, Jianghao, et al.
Pubblicazione: (2026)

MSVM-UNet: Multi-Scale Vision Mamba UNet for Medical Image Segmentation
di: Chen, Chaowei, et al.
Pubblicazione: (2024)