Image de couverture de livre

SmartFRZ: An Efficient Training Framework using Attention-Based Layer Freezing

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Sheng, Yuan, Geng, Dai, Yue, Zhang, Youtao, Wang, Yanzhi, Tang, Xulong
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

EdgeOL: Efficient in-situ Online Learning on Edge Devices
par: Li, Sheng, et autres
Publié: (2024)

Temporal Aware Pruning for Efficient Diffusion-based Video Generation
par: Li, Sheng, et autres
Publié: (2026)

Lotus: learning-based online thermal and latency variation management for two-stage detectors on edge devices
par: Gong, Yifan, et autres
Publié: (2024)

LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation
par: Xiao, Yang, et autres
Publié: (2025)

ToFe: Lagged Token Freezing and Reusing for Efficient Vision Transformer Inference
par: Zhang, Haoyue, et autres
Publié: (2025)

Efficient Training with Denoised Neural Weights
par: Gong, Yifan, et autres
Publié: (2024)

LVSA: Training-Free Sparse Attention for Long Video Diffusion
par: Glorian, Gael, et autres
Publié: (2026)

Head-Aware Visual Cropping: Enhancing Fine-Grained VQA with Attention-Guided Subimage
par: Xie, Junfei, et autres
Publié: (2026)

HeadRouter: A Training-free Image Editing Framework for MM-DiTs by Adaptively Routing Attention Heads
par: Xu, Yu, et autres
Publié: (2024)

Efficient Training of Diffusion Mixture-of-Experts Models: A Practical Recipe
par: Liu, Yahui, et autres
Publié: (2025)

Synthesizer Based Efficient Self-Attention for Vision Tasks
par: Zhu, Guangyang, et autres
Publié: (2022)

E$^{2}$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation
par: Gong, Yifan, et autres
Publié: (2024)

Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers
par: Liu, Yuxi, et autres
Publié: (2026)

Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling
par: Seo, Minhyuk, et autres
Publié: (2024)

SOLAR: Switchable Output Layer for Accuracy and Robustness in Once-for-All Training
par: Tareen, Shaharyar Ahmed Khan, et autres
Publié: (2025)

Attention-Based Variational Framework for Joint and Individual Components Learning with Applications in Brain Network Analysis
par: Zhang, Yifei, et autres
Publié: (2026)

Rethinking the Potential of Layer Freezing for Efficient DNN Training
par: Yang, Chence, et autres
Publié: (2025)

ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers
par: Yuan, Qianhao, et autres
Publié: (2025)

Enhancing Quantization-Aware Training on Edge Devices via Relative Entropy Coreset Selection and Cascaded Layer Correction
par: Tong, Yujia, et autres
Publié: (2025)

COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models
par: Xiao, Jinqi, et autres
Publié: (2023)

STAR: Stage-Wise Attention-Guided Token Reduction for Efficient Large Vision-Language Models Inference
par: Guo, Yichen, et autres
Publié: (2025)

EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training
par: Wang, Yulin, et autres
Publié: (2024)

Attention Frequency Modulation: Training-Free Spectral Modulation of Diffusion Cross-Attention
par: Oh, Seunghun, et autres
Publié: (2026)

Topology-preserving Adversarial Training for Alleviating Natural Accuracy Degradation
par: Mi, Xiaoyue, et autres
Publié: (2023)

ALTER: All-in-One Layer Pruning and Temporal Expert Routing for Efficient Diffusion Generation
par: Yang, Xiaomeng, et autres
Publié: (2025)

SuperLoRA: Parameter-Efficient Unified Adaptation of Multi-Layer Attention Modules
par: Chen, Xiangyu, et autres
Publié: (2024)

RoPeSLR: 3D RoPE-driven Sparse-LowRank Attention for Efficient Diffusion Transformers
par: Liu, Yuxi, et autres
Publié: (2026)

CORE: Code-based Inverse Self-Training Framework with Graph Expansion for Virtual Agents
par: Wang, Keyu, et autres
Publié: (2026)

SegMate: Asymmetric Attention-Based Lightweight Architecture for Efficient Multi-Organ Segmentation
par: Bunea, Andrei-Alexandru, et autres
Publié: (2026)

DiffDesign: Controllable Diffusion with Meta Prior for Efficient Interior Design Generation
par: Yang, Yuxuan, et autres
Publié: (2024)

Quantize-then-Rectify: Efficient VQ-VAE Training
par: Zhang, Borui, et autres
Publié: (2025)

AnchorFormer: Differentiable Anchor Attention for Efficient Vision Transformer
par: Shan, Jiquan, et autres
Publié: (2025)

Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-Training
par: Zhang, Wenyu, et autres
Publié: (2024)

Mixture-of-Top-k Attention: Efficient Attention via Scalable Fast Weights
par: Wen, Qishuai, et autres
Publié: (2026)

Learning to Generate Gradients for Test-Time Adaptation via Test-Time Training Layers
par: Deng, Qi, et autres
Publié: (2024)

FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation
par: Yang, Kaixing, et autres
Publié: (2025)

Read Between the Layers: Leveraging Multi-Layer Representations for Rehearsal-Free Continual Learning with Pre-Trained Models
par: Ahrens, Kyra, et autres
Publié: (2023)

SmartSight: Mitigating Hallucination in Video-LLMs Without Compromising Video Understanding via Temporal Attention Collapse
par: Sun, Yiming, et autres
Publié: (2025)

Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networks
par: Zhao, Pu, et autres
Publié: (2019)

Plug-in Feedback Self-adaptive Attention in CLIP for Training-free Open-Vocabulary Segmentation
par: Chi, Zhixiang, et autres
Publié: (2025)