Imagen de Portada

Beyond MACs: Hardware Efficient Architecture Design for Vision Backbones

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Nottebaum, Moritz, Dunnhofer, Matteo, Micheloni, Christian
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

CPUBone: Efficient Vision Backbone Design for Devices with Low Parallelization Capabilities
por: Nottebaum, Moritz, et al.
Publicado: (2026)

LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones
por: Nottebaum, Moritz, et al.
Publicado: (2024)

Tracking Skiers from the Top to the Bottom
por: Dunnhofer, Matteo, et al.
Publicado: (2023)

Is Tracking really more challenging in First Person Egocentric Vision?
por: Dunnhofer, Matteo, et al.
Publicado: (2025)

Better, But Not Sufficient: Testing Video ANNs Against Macaque IT Dynamics
por: Dunnhofer, Matteo, et al.
Publicado: (2026)

Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory
por: Manigrasso, Zaira, et al.
Publicado: (2024)

SkelMamba: A State Space Model for Efficient Skeleton Action Recognition of Neurological Disorders
por: Martinel, Niki, et al.
Publicado: (2024)

Revisiting the Integration of Convolution and Attention for Vision Backbone
por: Zhu, Lei, et al.
Publicado: (2024)

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

ReMAR-DS: Recalibrated Feature Learning for Metal Artifact Reduction and CT Domain Transformation
por: Rehman, Mubashara, et al.
Publicado: (2025)

Vision Backbone Efficient Selection for Image Classification in Low-Data Regimes
por: Guerin, Joris, et al.
Publicado: (2024)

Vision-LSTM: xLSTM as Generic Vision Backbone
por: Alkin, Benedikt, et al.
Publicado: (2024)

MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining
por: Liu, Yunze, et al.
Publicado: (2024)

CoMViT: An Efficient Vision Backbone for Supervised Classification in Medical Imaging
por: Safdar, Aon, et al.
Publicado: (2025)

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

Beyond Attention Scores: SVD-Based Vision Token Pruning for Efficient Vision-Language Models
por: Apedo, Yvon, et al.
Publicado: (2026)

CASA: Cross-Attention over Self-Attention for Efficient Vision-Language Fusion
por: Böhle, Moritz, et al.
Publicado: (2025)

Back to the Barn with LLAMAs: Evolving Pretrained LLM Backbones in Finetuning Vision Language Models
por: Horawalavithana, Sameera, et al.
Publicado: (2026)

Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation
por: Barsellotti, Luca, et al.
Publicado: (2024)

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

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

SAFE-KD: Risk-Controlled Early-Exit Distillation for Vision Backbones
por: Khazem, Salim
Publicado: (2026)

Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising
por: Saied, Youssef, et al.
Publicado: (2026)

A Survey on Backbones for Deep Video Action Recognition
por: Tang, Zixuan, et al.
Publicado: (2024)

Tighnari: Multi-modal Plant Species Prediction Based on Hierarchical Cross-Attention Using Graph-Based and Vision Backbone-Extracted Features
por: Liu, Haixu, et al.
Publicado: (2025)

ForestProtector: An IoT Architecture Integrating Machine Vision and Deep Reinforcement Learning for Efficient Wildfire Monitoring
por: Bonilla-Ormachea, Kenneth, et al.
Publicado: (2025)

Self-Supervised Backbone Framework for Diverse Agricultural Vision Tasks
por: Sornapudi, Sudhir, et al.
Publicado: (2024)

RapidNet: Multi-Level Dilated Convolution Based Mobile Backbone
por: Munir, Mustafa, et al.
Publicado: (2024)

A Generic Shared Attention Mechanism for Various Backbone Neural Networks
por: Huang, Zhongzhan, et al.
Publicado: (2022)

A Survey on Mamba Architecture for Vision Applications
por: Ibrahim, Fady, et al.
Publicado: (2025)

EdgeDiT: Hardware-Aware Diffusion Transformers for Efficient On-Device Image Generation
por: Kodavanti, Sravanth, et al.
Publicado: (2026)

Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching
por: Shao, Shitong, et al.
Publicado: (2023)

Enhancing LLM-Based Neural Network Generation: Few-Shot Prompting and Efficient Validation for Automated Architecture Design
por: Duvvuri, Raghuvir, et al.
Publicado: (2025)

Beyond ZOH: Advanced Discretization Strategies for Vision Mamba
por: Ibrahim, Fady, et al.
Publicado: (2026)

Pretraining Objective Matters in Extreme Low-Data FGVC: A Backbone-Controlled Study
por: Hackett, Alexander, et al.
Publicado: (2026)

X-Distill: Cross-Architecture Vision Distillation for Visuomotor Learning
por: Shao, Maanping, et al.
Publicado: (2026)

Empowering Backbone Models for Visual Text Generation with Input Granularity Control and Glyph-Aware Training
por: Li, Wenbo, et al.
Publicado: (2024)

Masked Modeling for Self-supervised Representation Learning on Vision and Beyond
por: Li, Siyuan, et al.
Publicado: (2023)

Beyond the Visible: Multispectral Vision-Language Learning for Earth Observation
por: Marimo, Clive Tinashe, et al.
Publicado: (2025)

Data Metabolism: An Efficient Data Design Schema For Vision Language Model
por: Zhang, Jingyuan, et al.
Publicado: (2025)