Cover Image

CubistMerge: Spatial-Preserving Token Merging For Diverse ViT Backbones

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gong, Wenyi, Lis, Mieszko
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models
by: Nguyen, Duy M. H., et al.
Published: (2026)

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

Efficient Visual Transformer by Learnable Token Merging
by: Wang, Yancheng, et al.
Published: (2024)

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

DC-Merge: Improving Model Merging with Directional Consistency
by: Zhang, Han-Chen, et al.
Published: (2026)

ViT Enhanced Privacy-Preserving Secure Medical Data Sharing and Classification
by: Amin, Al, et al.
Published: (2024)

Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding
by: Zhang, Yiming, et al.
Published: (2024)

How to train your ViT for OOD Detection
by: Mueller, Maximilian, et al.
Published: (2024)

AdaMerging: Adaptive Model Merging for Multi-Task Learning
by: Yang, Enneng, et al.
Published: (2023)

EMR-Merging: Tuning-Free High-Performance Model Merging
by: Huang, Chenyu, et al.
Published: (2024)

Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging
by: Guo, Kuangpu, et al.
Published: (2025)

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

LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging
by: Kim, Jinuk, et al.
Published: (2024)

Stylizing ViT: Anatomy-Preserving Instance Style Transfer for Domain Generalization
by: Doerrich, Sebastian, et al.
Published: (2026)

ZACH-ViT: A Zero-Token Vision Transformer with ShuffleStrides Data Augmentation for Robust Lung Ultrasound Classification
by: Angelakis, Athanasios, et al.
Published: (2025)

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

SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding
by: Wang, Haoxiang, et al.
Published: (2023)

TPC-ViT: Token Propagation Controller for Efficient Vision Transformer
by: Zhu, Wentao
Published: (2024)

Saliency-Aware Model Merging
by: Park, Jungin, et al.
Published: (2026)

CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving
by: Yang, Huitong, et al.
Published: (2025)

ATM: Improving Model Merging by Alternating Tuning and Merging
by: Zhou, Luca, et al.
Published: (2024)

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

ProtoS-ViT: Visual foundation models for sparse self-explainable classifications
by: Turbé, Hugues, et al.
Published: (2024)

Segformer++: Efficient Token-Merging Strategies for High-Resolution Semantic Segmentation
by: Kienzle, Daniel, et al.
Published: (2024)

Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis
by: Horoi, Stefan, et al.
Published: (2024)

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

Layer by layer, module by module: Choose both for optimal OOD probing of ViT
by: Odonnat, Ambroise, et al.
Published: (2026)

Negative Token Merging: Image-based Adversarial Feature Guidance
by: Singh, Jaskirat, et al.
Published: (2024)

D$^{3}$ToM: Decider-Guided Dynamic Token Merging for Accelerating Diffusion MLLMs
by: Chang, Shuochen, et al.
Published: (2025)

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

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

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

ToSA: Token Merging with Spatial Awareness
by: Huang, Hsiang-Wei, et al.
Published: (2025)

ViR: Towards Efficient Vision Retention Backbones
by: Hatamizadeh, Ali, et al.
Published: (2023)

Register and [CLS] tokens yield a decoupling of local and global features in large ViTs
by: Lappe, Alexander, et al.
Published: (2025)

GrowTAS: Progressive Expansion from Small to Large Subnets for Efficient ViT Architecture Search
by: Lee, Hyunju, et al.
Published: (2025)

ChAda-ViT : Channel Adaptive Attention for Joint Representation Learning of Heterogeneous Microscopy Images
by: Bourriez, Nicolas, et al.
Published: (2023)

ViT-MUL: A Baseline Study on Recent Machine Unlearning Methods Applied to Vision Transformers
by: Cho, Ikhyun, et al.
Published: (2024)