Imagen de Portada

Memory-Efficient Vision Transformers: An Activation-Aware Mixed-Rank Compression Strategy

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Azizi, Seyedarmin, Nazemi, Mahdi, Pedram, Massoud
Formato:	Preprint
Publicado:	2024
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

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

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

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

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

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

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

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

HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact Neural Networks
por: Xiao, Jinqi, et al.
Publicado: (2023)

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

Weight Copy and Low-Rank Adaptation for Few-Shot Distillation of Vision Transformers
por: Grigore, Diana-Nicoleta, et al.
Publicado: (2024)

AdapterTune: Zero-Initialized Low-Rank Adapters for Frozen Vision Transformers
por: Khazem, Salim
Publicado: (2026)

COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models
por: Xiao, Jinqi, et al.
Publicado: (2023)

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers
por: You, Haoran, et al.
Publicado: (2024)

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

Vision Hopfield Memory Networks
por: Wang, Jianfeng, et al.
Publicado: (2026)

TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration
por: Olszewski, Jan, et al.
Publicado: (2023)

I-Segmenter: Integer-Only Vision Transformer for Efficient Semantic Segmentation
por: Sassoon, Jordan, et al.
Publicado: (2025)

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

EUDA: An Efficient Unsupervised Domain Adaptation via Self-Supervised Vision Transformer
por: Abedi, Ali, et al.
Publicado: (2024)

Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications
por: Hu, Zixuan, et al.
Publicado: (2025)

SwapTransformer: highway overtaking tactical planner model via imitation learning on OSHA dataset
por: Shamsoshoara, Alireza, et al.
Publicado: (2024)

COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection
por: Xiao, Jinqi, et al.
Publicado: (2024)

C-SWAP: Explainability-Aware Structured Pruning for Efficient Neural Networks Compression
por: Bauvin, Baptiste, et al.
Publicado: (2025)

Activation Matters: Test-time Activated Negative Labels for OOD Detection with Vision-Language Models
por: Zhang, Yabin, et al.
Publicado: (2026)

Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta Compression
por: Wang, Xiaohui, et al.
Publicado: (2025)

VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models
por: Yu, Xinlei, et al.
Publicado: (2025)

Transformer Model for Alzheimer's Disease Progression Prediction Using Longitudinal Visit Sequences
por: Moghaddami, Mahdi, et al.
Publicado: (2025)

Point-LN: A Lightweight Framework for Efficient Point Cloud Classification Using Non-Parametric Positional Encoding
por: Mohammadi, Marzieh, et al.
Publicado: (2025)

Enhancing kelp forest detection in remote sensing images using crowdsourced labels with Mixed Vision Transformers and ConvNeXt segmentation models
por: Nasios, Ioannis
Publicado: (2025)

MixMask: Revisiting Masking Strategy for Siamese ConvNets
por: Vishniakov, Kirill, et al.
Publicado: (2022)

HyDRA: Hierarchical and Dynamic Rank Adaptation for Mobile Vision Language Model
por: Xi, Yuanhao, et al.
Publicado: (2025)

DMODE: Differential Monocular Object Distance Estimation Module without Class Specific Information
por: Agand, Pedram, et al.
Publicado: (2022)

Improving Interpretation Faithfulness for Vision Transformers
por: Hu, Lijie, et al.
Publicado: (2023)

Block-Recurrent Dynamics in Vision Transformers
por: Jacobs, Mozes, et al.
Publicado: (2025)

Memory-Efficient Continual Learning Object Segmentation for Long Video
por: Nazemi, Amir, et al.
Publicado: (2023)

Structured Unrestricted-Rank Matrices for Parameter Efficient Fine-tuning
por: Sehanobish, Arijit, et al.
Publicado: (2024)

FastVLM: Efficient Vision Encoding for Vision Language Models
por: Vasu, Pavan Kumar Anasosalu, et al.
Publicado: (2024)

ADAPT to Robustify Prompt Tuning Vision Transformers
por: Eskandar, Masih, et al.
Publicado: (2024)

Continual Adaptation of Vision Transformers for Federated Learning
por: Halbe, Shaunak, et al.
Publicado: (2023)

Mechanisms of Non-Monotonic Scaling in Vision Transformers
por: Kumar, Anantha Padmanaban Krishna
Publicado: (2025)