Cover Image

Training-Free Acceleration of ViTs with Delayed Spatial Merging

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Heo, Jung Hwan, Azizi, Seyedarmin, Fayyazi, Arash, Pedram, Massoud
Format:	Preprint
Published:	2023
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PEANO-ViT: Power-Efficient Approximations of Non-Linearities in Vision Transformers
by: Sadeghi, Mohammad Erfan, et al.
Published: (2024)

Memory-Efficient Vision Transformers: An Activation-Aware Mixed-Rank Compression Strategy
by: Azizi, Seyedarmin, et al.
Published: (2024)

Efficient Noise Mitigation for Enhancing Inference Accuracy in DNNs on Mixed-Signal Accelerators
by: Azizi, Seyedarmin, et al.
Published: (2024)

Sensitivity-Aware Mixed-Precision Quantization and Width Optimization of Deep Neural Networks Through Cluster-Based Tree-Structured Parzen Estimation
by: Azizi, Seyedarmin, et al.
Published: (2023)

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

FAIR-SIGHT: Fairness Assurance in Image Recognition via Simultaneous Conformal Thresholding and Dynamic Output Repair
by: Fayyazi, Arya, et al.
Published: (2025)

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

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

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

TAP-ViTs: Task-Adaptive Pruning for On-Device Deployment of Vision Transformers
by: Wang, Zhibo, et al.
Published: (2026)

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

CHOSEN: Compilation to Hardware Optimization Stack for Efficient Vision Transformer Inference
by: Sadeghi, Mohammad Erfan, et al.
Published: (2024)

Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness
by: Elisha, Yehonatan, et al.
Published: (2026)

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

Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision Transformer
by: Shi, Huihong, et al.
Published: (2024)

LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation
by: Azizi, Seyedarmin, et al.
Published: (2024)

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

Activation Steering for Chain-of-Thought Compression
by: Azizi, Seyedarmin, et al.
Published: (2025)

TransForSeg: A Multitask Stereo ViT for Joint Stereo Segmentation and 3D Force Estimation in Catheterization
by: Fekri, Pedram, et al.
Published: (2025)

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

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

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

CubistMerge: Spatial-Preserving Token Merging For Diverse ViT Backbones
by: Gong, Wenyi, et al.
Published: (2025)

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

MobilePlantViT: A Mobile-friendly Hybrid ViT for Generalized Plant Disease Image Classification
by: Tonmoy, Moshiur Rahman, et al.
Published: (2025)

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

Dynamic Co-Optimization Compiler: Leveraging Multi-Agent Reinforcement Learning for Enhanced DNN Accelerator Performance
by: Fayyazi, Arya, et al.
Published: (2024)

LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition
by: Hu, Youbing, et al.
Published: (2024)

Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers
by: Li, Zhengang, et al.
Published: (2024)

DFQ-ViT: Data-Free Quantization for Vision Transformers without Fine-tuning
by: Tong, Yujia, et al.
Published: (2025)

Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation
by: Potraghloo, Erfan Baghaei, et al.
Published: (2025)

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

ViT-ProtoNet for Few-Shot Image Classification: A Multi-Benchmark Evaluation
by: Mutlu, Abdulvahap, et al.
Published: (2025)

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

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

How Can Multimodal Remote Sensing Datasets Transform Classification via SpatialNet-ViT?
by: Kashyap, Gautam Siddharth, 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)

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

OmniPatch: A Universal Adversarial Patch for ViT-CNN Cross-Architecture Transfer in Semantic Segmentation
by: Aggarwal, Aarush, et al.
Published: (2026)