Copertina

Data-independent Module-aware Pruning for Hierarchical Vision Transformers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	He, Yang, Zhou, Joey Tianyi
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning
di: Zhang, Xin, et al.
Pubblicazione: (2023)

Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator
di: Zhang, Xin, et al.
Pubblicazione: (2024)

The Effects of Grouped Structural Global Pruning of Vision Transformers on Domain Generalisation
di: Riaz, Hamza, et al.
Pubblicazione: (2025)

Iwin Transformer: Hierarchical Vision Transformer using Interleaved Windows
di: Huo, Simin, et al.
Pubblicazione: (2025)

Batch Loss Score for Dynamic Data Pruning
di: Zhou, Qing, et al.
Pubblicazione: (2026)

SCOPE: Saliency-Coverage Oriented Token Pruning for Efficient Multimodel LLMs
di: Deng, Jinhong, et al.
Pubblicazione: (2025)

Cross-modal Active Complementary Learning with Self-refining Correspondence
di: Qin, Yang, et al.
Pubblicazione: (2023)

Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustment
di: Du, Jiawei, et al.
Pubblicazione: (2024)

Beyond Modality Collapse: Representations Blending for Multimodal Dataset Distillation
di: Zhang, Xin, et al.
Pubblicazione: (2025)

HiAP: A Multi-Granular Stochastic Auto-Pruning Framework for Vision Transformers
di: Li, Andy, et al.
Pubblicazione: (2026)

Rethinking Pruning for Vision-Language Models: Strategies for Effective Sparsity and Performance Restoration
di: He, Shwai, et al.
Pubblicazione: (2024)

Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models
di: Li, Yue, et al.
Pubblicazione: (2025)

Pruning One More Token is Enough: Leveraging Latency-Workload Non-Linearities for Vision Transformers on the Edge
di: Eliopoulos, Nick John, et al.
Pubblicazione: (2024)

CORP: Closed-Form One-shot Representation-Preserving Structured Pruning for Transformers
di: Zhang, Boxiang, et al.
Pubblicazione: (2026)

Distilling the Knowledge in Data Pruning
di: Ben-Baruch, Emanuel, et al.
Pubblicazione: (2024)

Large-scale Dataset Pruning with Dynamic Uncertainty
di: He, Muyang, et al.
Pubblicazione: (2023)

A Greedy Hierarchical Approach to Whole-Network Filter-Pruning in CNNs
di: Purohit, Kiran, et al.
Pubblicazione: (2024)

Multimodal-Guided Dynamic Dataset Pruning for Robust and Efficient Data-Centric Learning
di: Yang, Suorong, et al.
Pubblicazione: (2025)

Training-Free Dataset Pruning for Instance Segmentation
di: Dai, Yalun, et al.
Pubblicazione: (2025)

PruneFuse: Efficient Data Selection via Weight Pruning and Network Fusion
di: Kousar, Humaira, et al.
Pubblicazione: (2026)

ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers
di: Sinha, Sanchit, et al.
Pubblicazione: (2025)

Data Pruning in Generative Diffusion Models
di: Briq, Rania, et al.
Pubblicazione: (2024)

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

Ensembling Pruned Attention Heads For Uncertainty-Aware Efficient Transformers
di: Gabetni, Firas, et al.
Pubblicazione: (2025)

Fairness-aware Vision Transformer via Debiased Self-Attention
di: Qiang, Yao, et al.
Pubblicazione: (2023)

DRoP: Distributionally Robust Data Pruning
di: Vysogorets, Artem, et al.
Pubblicazione: (2024)

FasterViT: Fast Vision Transformers with Hierarchical Attention
di: Hatamizadeh, Ali, et al.
Pubblicazione: (2023)

Isomorphic Pruning for Vision Models
di: Fang, Gongfan, et al.
Pubblicazione: (2024)

Compact Vision Transformer by Reduction of Kernel Complexity
di: Wang, Yancheng, et al.
Pubblicazione: (2025)

Decay Pruning Method: Smooth Pruning With a Self-Rectifying Procedure
di: Yang, Minghao, et al.
Pubblicazione: (2024)

OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization
di: Meng, Xiang, et al.
Pubblicazione: (2024)

LOTUS: Improving Transformer Efficiency with Sparsity Pruning and Data Lottery Tickets
di: Upadhyay, Ojasw
Pubblicazione: (2024)

Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space
di: Pan, Linchao, et al.
Pubblicazione: (2025)

Knowledge-aware Graph Transformer for Pedestrian Trajectory Prediction
di: Liu, Yu, et al.
Pubblicazione: (2024)

HQViT: Hybrid Quantum Vision Transformer for Image Classification
di: Zhang, Hui, et al.
Pubblicazione: (2025)

Focus Your Attention: Towards Data-Intuitive Lightweight Vision Transformers
di: Gaurav, Suyash, et al.
Pubblicazione: (2025)

CRISP: Hybrid Structured Sparsity for Class-aware Model Pruning
di: Aggarwal, Shivam, et al.
Pubblicazione: (2023)

Steering Sparse Autoencoder Latents to Control Dynamic Head Pruning in Vision Transformers (Student Abstract)
di: Lee, Yousung, et al.
Pubblicazione: (2026)

CAPA: Contribution-Aware Pruning and FFN Approximation for Efficient Large Vision-Language Models
di: Jha, Samyak, et al.
Pubblicazione: (2026)

Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers
di: Hatefi, Sayed Mohammad Vakilzadeh, et al.
Pubblicazione: (2024)