Copertina

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Guoxin, Wang, Qingyuan, Huang, Binhua, Chen, Shaowu, John, Deepu
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models
di: Arif, Kazi Hasan Ibn, et al.
Pubblicazione: (2024)

Optimal Brain Connection: Towards Efficient Structural Pruning
di: Chen, Shaowu, et al.
Pubblicazione: (2025)

MoCrop: Training Free Motion Guided Cropping for Efficient Video Action Recognition
di: Huang, Binhua, et al.
Pubblicazione: (2025)

Tiny-Engram: Trigger-Indexed Concept Tables for Generative Vision
di: Cai, Runyuan, et al.
Pubblicazione: (2026)

Heterogeneous Graph Transformer for Multiple Tiny Object Tracking in RGB-T Videos
di: Xu, Qingyu, et al.
Pubblicazione: (2024)

TinyFusion: Diffusion Transformers Learned Shallow
di: Fang, Gongfan, et al.
Pubblicazione: (2024)

StreamTinyNet: video streaming analysis with spatial-temporal TinyML
di: Shalby, Hazem Hesham Yousef, et al.
Pubblicazione: (2024)

Tiny-ViT: A Compact Vision Transformer for Efficient and Explainable Potato Leaf Disease Classification
di: Mia, Shakil, et al.
Pubblicazione: (2026)

TinyFormer: Preserving Tiny Objects in YOLO-DETR Hybrid Real-time Detectors
di: Hsieh, Jun-Wei, et al.
Pubblicazione: (2026)

Variation-aware Vision Token Dropping for Faster Large Vision-Language Models
di: Chen, Junjie, et al.
Pubblicazione: (2025)

TinyLVLM-eHub: Towards Comprehensive and Efficient Evaluation for Large Vision-Language Models
di: Shao, Wenqi, et al.
Pubblicazione: (2023)

Tiny Machine Learning: Progress and Futures
di: Lin, Ji, et al.
Pubblicazione: (2024)

AttentionDrop: A Novel Regularization Method for Transformer Models
di: Baig, Mirza Samad Ahmed, et al.
Pubblicazione: (2025)

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning
di: Chien, Tzu-Chun, et al.
Pubblicazione: (2025)

Noise-Robust Tiny Object Localization with Flows
di: Sun, Huixin, et al.
Pubblicazione: (2026)

EvRainDrop: HyperGraph-guided Completion for Effective Frame and Event Stream Aggregation
di: Wang, Futian, et al.
Pubblicazione: (2025)

ORXE: Orchestrating Experts for Dynamically Configurable Efficiency
di: Wang, Qingyuan, et al.
Pubblicazione: (2025)

SAM-Sode: Towards Faithful Explanations for Tiny Bacteria Detection
di: Tan, Wanying, et al.
Pubblicazione: (2026)

Wake Vision: A Tailored Dataset and Benchmark Suite for TinyML Computer Vision Applications
di: Banbury, Colby, et al.
Pubblicazione: (2024)

LogTinyLLM: Tiny Large Language Models Based Contextual Log Anomaly Detection
di: Ocansey, Isaiah Thompson, et al.
Pubblicazione: (2025)

TinyViT-Batten: Few-Shot Vision Transformer with Explainable Attention for Early Batten-Disease Detection on Pediatric MRI
di: Uppalapati, Khartik, et al.
Pubblicazione: (2025)

TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks
di: Hu, Yuanze, et al.
Pubblicazione: (2025)

TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model
di: Ding, Zhaoyuan, et al.
Pubblicazione: (2026)

Scale-Aware Relay and Scale-Adaptive Loss for Tiny Object Detection in Aerial Images
di: Li, Jinfu, et al.
Pubblicazione: (2025)

Not Like Transformers: Drop the Beat Representation for Dance Generation with Mamba-Based Diffusion Model
di: Park, Sangjune, et al.
Pubblicazione: (2026)

Multi-modal Spatio-Temporal Transformer for High-resolution Land Subsidence Prediction
di: Yao, Wendong, et al.
Pubblicazione: (2025)

TinyVLM: Zero-Shot Object Detection on Microcontrollers via Vision-Language Distillation with Matryoshka Embeddings
di: Wilson, Bibin
Pubblicazione: (2026)

TinySSL: Distilled Self-Supervised Pretraining for Sub-Megabyte MCU Models
di: Wilson, Bibin
Pubblicazione: (2026)

Tiny Inference-Time Scaling with Latent Verifiers
di: Bucciarelli, Davide, et al.
Pubblicazione: (2026)

FastTab: A Fast Table Recognizer with a Tiny Recursive Module and 1D Transformers
di: Hamdi, Laziz, et al.
Pubblicazione: (2026)

NubbleDrop: A Simple Way to Improve Matching Strategy for Prompted One-Shot Segmentation
di: Xu, Zhiyu, et al.
Pubblicazione: (2024)

CoilDrop-MRI: Self-supervised physics-guided MRI reconstruction with coil dropout
di: Song, Tongxi, et al.
Pubblicazione: (2026)

Tiny Models are the Computational Saver for Large Models
di: Wang, Qingyuan, et al.
Pubblicazione: (2024)

TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba
di: Ma, Xiaowen, et al.
Pubblicazione: (2024)

Rethinking Token Reduction for Large Vision-Language Models
di: Wang, Yi, et al.
Pubblicazione: (2026)

COXNet: Cross-Layer Fusion with Adaptive Alignment and Scale Integration for RGBT Tiny Object Detection
di: Peng, Peiran, et al.
Pubblicazione: (2025)

TinyEcoWeedNet: Edge Efficient Real-Time Aerial Agricultural Weed Detection
di: Khater, Omar H., et al.
Pubblicazione: (2025)

Evaluation of GPT-4o and GPT-4o-mini's Vision Capabilities for Compositional Analysis from Dried Solution Drops
di: Dangi, Deven B., et al.
Pubblicazione: (2024)

GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation
di: Xu, Xuwei, et al.
Pubblicazione: (2023)

Simple Drop-in LoRA Conditioning on Attention Layers Will Improve Your Diffusion Model
di: Choi, Joo Young, et al.
Pubblicazione: (2024)