Image de couverture de livre

Separate, Dynamic and Differentiable (SMART) Pruner for Block/Output Channel Pruning on Computer Vision Tasks

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ding, Guanhua, Ye, Zexi, Zhong, Zhen, Li, Gang, Shao, David
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights
par: Castells, Thibault, et autres
Publié: (2024)

AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models
par: Baek, Changwoo, et autres
Publié: (2026)

VLM-Pruner: Buffering for Spatial Sparsity in an Efficient VLM Centrifugal Token Pruning Paradigm
par: Wu, Zhenkai, et autres
Publié: (2025)

LearnPruner: Rethinking Attention-based Token Pruning in Vision Language Models
par: Takezoe, Rinyoichi, et autres
Publié: (2026)

Multi-Dimensional Pruning: Joint Channel, Layer and Block Pruning with Latency Constraint
par: Sun, Xinglong, et autres
Publié: (2024)

D2Pruner: Debiased Importance and Structural Diversity for MLLM Token Pruning
par: Zhang, Evelyn, et autres
Publié: (2025)

SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation
par: Ma, Shilin, et autres
Publié: (2026)

MedPruner: Training-Free Hierarchical Token Pruning for Efficient 3D Medical Image Understanding in Vision-Language Models
par: Liu, Shengyuan, et autres
Publié: (2026)

RCP: Representation Consistency Pruner for Mitigating Distribution Shift in Large Vision-Language Models
par: Zhang, Jianwei, et autres
Publié: (2026)

Block-Recurrent Dynamics in Vision Transformers
par: Jacobs, Mozes, et autres
Publié: (2025)

MI-Pruner: Crossmodal Mutual Information-guided Token Pruner for Efficient MLLMs
par: Li, Jiameng, et autres
Publié: (2026)

RL-Pruner: Structured Pruning Using Reinforcement Learning for CNN Compression and Acceleration
par: Wang, Boyao, et autres
Publié: (2024)

TAP-ViTs: Task-Adaptive Pruning for On-Device Deployment of Vision Transformers
par: Wang, Zhibo, et autres
Publié: (2026)

Leveraging Perceptual Scores for Dataset Pruning in Computer Vision Tasks
par: Singh, Raghavendra
Publié: (2024)

Pruning by Block Benefit: Exploring the Properties of Vision Transformer Blocks during Domain Adaptation
par: Glandorf, Patrick, et autres
Publié: (2025)

Block-based Symmetric Pruning and Fusion for Efficient Vision Transformers
par: Hsieh, Yi-Kuan, et autres
Publié: (2025)

Task-based Loss Functions in Computer Vision: A Comprehensive Review
par: Elharrouss, Omar, et autres
Publié: (2025)

Rethinking Low-Rank Adaptation in Vision: Exploring Head-Level Responsiveness across Diverse Tasks
par: Zhong, Yibo, et autres
Publié: (2024)

Multimodal-Guided Dynamic Dataset Pruning for Robust and Efficient Data-Centric Learning
par: Yang, Suorong, et autres
Publié: (2025)

SynthVision -- Harnessing Minimal Input for Maximal Output in Computer Vision Models using Synthetic Image data
par: Kularathne, Yudara, et autres
Publié: (2024)

Isomorphic Pruning for Vision Models
par: Fang, Gongfan, et autres
Publié: (2024)

AutoDFP: Automatic Data-Free Pruning via Channel Similarity Reconstruction
par: Li, Siqi, et autres
Publié: (2024)

Data-independent Module-aware Pruning for Hierarchical Vision Transformers
par: He, Yang, et autres
Publié: (2024)

Learning to Rank Pre-trained Vision-Language Models for Downstream Tasks
par: Ding, Yuhe, et autres
Publié: (2024)

ChannelExplorer: Exploring Class Separability Through Activation Channel Visualization
par: Zaman, Md Rahat-uz-, et autres
Publié: (2025)

DMTG: One-Shot Differentiable Multi-Task Grouping
par: Gao, Yuan, et autres
Publié: (2024)

Large-scale Dataset Pruning with Dynamic Uncertainty
par: He, Muyang, et autres
Publié: (2023)

Batch Loss Score for Dynamic Data Pruning
par: Zhou, Qing, et autres
Publié: (2026)

UPDP: A Unified Progressive Depth Pruner for CNN and Vision Transformer
par: Liu, Ji, et autres
Publié: (2024)

SMART-Vision: Survey of Modern Action Recognition Techniques in Vision
par: AlShami, Ali K., et autres
Publié: (2025)

Block Selective Reprogramming for On-device Training of Vision Transformers
par: Sarkar, Sreetama, et autres
Publié: (2024)

MABViT -- Modified Attention Block Enhances Vision Transformers
par: Ramesh, Mahesh, et autres
Publié: (2023)

The Effects of Grouped Structural Global Pruning of Vision Transformers on Domain Generalisation
par: Riaz, Hamza, et autres
Publié: (2025)

IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning
par: Sun, Zhichao, et autres
Publié: (2026)

AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision Tasks
par: Yang, Zekang, et autres
Publié: (2024)

Automatic Complementary Separation Pruning Toward Lightweight CNNs
par: Levin, David, et autres
Publié: (2025)

Redefining non-IID Data in Federated Learning for Computer Vision Tasks: Migrating from Labels to Embeddings for Task-Specific Data Distributions
par: Borazjani, Kasra, et autres
Publié: (2025)

MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning
par: Farina, Matteo, et autres
Publié: (2024)

SGW-based Multi-Task Learning in Vision Tasks
par: Zhang, Ruiyuan, et autres
Publié: (2024)

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models
par: Wang, Qinsi, et autres
Publié: (2025)