Image de couverture de livre

EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Longfei, Hou, Yongjie, Li, Yang, Wang, Qirui, Sha, Youyang, Yu, Yongjun, Wang, Yinzhi, Ru, Peizhe, Yu, Xuanlong, Shen, Xi
Format:	Preprint
Publié:	2026
Sujets:	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

A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helps
par: Yu, Xuanlong, et autres
Publié: (2026)

FSOD-VFM: Few-Shot Object Detection with Vision Foundation Models and Graph Diffusion
par: Feng, Chen-Bin, et autres
Publié: (2026)

From Misclassifications to Outliers: Joint Reliability Assessment in Classification
par: Li, Yang, et autres
Publié: (2026)

Real-Time Object Detection Meets DINOv3
par: Huang, Shihua, et autres
Publié: (2025)

Refining Datapath for Microscaling ViTs
par: Xiao, Can, et autres
Publié: (2025)

Purrturbed but Stable: Human-Cat Invariant Representations Across CNNs, ViTs and Self-Supervised ViTs
par: Shah, Arya, et autres
Publié: (2025)

DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs
par: Kim, Donghyun, et autres
Publié: (2024)

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

Token Cropr: Faster ViTs for Quite a Few Tasks
par: Bergner, Benjamin, et autres
Publié: (2024)

Fusing Pretrained ViTs with TCNet for Enhanced EEG Regression
par: Modesitt, Eric, et autres
Publié: (2024)

U-REPA: Aligning Diffusion U-Nets to ViTs
par: Tian, Yuchuan, et autres
Publié: (2025)

Intriguing Frequency Interpretation of Adversarial Robustness for CNNs and ViTs
par: Chen, Lu, et autres
Publié: (2025)

I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization
par: Zhong, Yunshan, et autres
Publié: (2023)

CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs
par: Ramachandran, Akshat, et autres
Publié: (2024)

STRAP-ViT: Segregated Tokens with Randomized -- Transformations for Defense against Adversarial Patches in ViTs
par: Chattopadhyay, Nandish, et autres
Publié: (2026)

Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability
par: Liu, Jiani, et autres
Publié: (2025)

Elastic ViTs from Pretrained Models without Retraining
par: Simoncini, Walter, et autres
Publié: (2025)

Training-Free Acceleration of ViTs with Delayed Spatial Merging
par: Heo, Jung Hwan, et autres
Publié: (2023)

Pretrained ViTs Yield Versatile Representations For Medical Images
par: Matsoukas, Christos, et autres
Publié: (2023)

Octic Vision Transformers: Quicker ViTs Through Equivariance
par: Nordström, David, et autres
Publié: (2025)

VIVID-Med: LLM-Supervised Structured Pretraining for Deployable Medical ViTs
par: Wang, Xiyao, et autres
Publié: (2026)

Which Direction to Choose? An Analysis on the Representation Power of Self-Supervised ViTs in Downstream Tasks
par: Kaltampanidis, Yannis, et autres
Publié: (2025)

ConcatPlexer: Additional Dim1 Batching for Faster ViTs
par: Han, Donghoon, et autres
Publié: (2023)

Colinearity Decay: Training Quantization-Friendly ViTs with Outlier Decay
par: Tong, Jin, et autres
Publié: (2026)

Adapting Pretrained ViTs with Convolution Injector for Visuo-Motor Control
par: Hwang, Dongyoon, et autres
Publié: (2024)

ViTs: Teaching Machines to See Time Series Anomalies Like Human Experts
par: Wang, Zexin, et autres
Publié: (2025)

Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey
par: Siméoni, Oriane, et autres
Publié: (2023)

Communication Efficient Split Learning of ViTs with Attention-based Double Compression
par: Alvetreti, Federico, et autres
Publié: (2025)

Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP
par: Balasubramanian, Sriram, et autres
Publié: (2024)

DS-ViT: Dual-Stream Vision Transformer for Cross-Task Distillation in Alzheimer's Early Diagnosis
par: Chen, Ke, et autres
Publié: (2024)

CAIT: Triple-Win Compression towards High Accuracy, Fast Inference, and Favorable Transferability For ViTs
par: Wang, Ao, et autres
Publié: (2023)

ViTs are Everywhere: A Comprehensive Study Showcasing Vision Transformers in Different Domain
par: Mia, Md Sohag, et autres
Publié: (2023)

Parameter Efficient Fine-tuning of Self-supervised ViTs without Catastrophic Forgetting
par: Bafghi, Reza Akbarian, et autres
Publié: (2024)

Exploring the Synergies of Hybrid CNNs and ViTs Architectures for Computer Vision: A survey
par: Yunusa, Haruna, et autres
Publié: (2024)

Causality $\neq$ Decodability, and Vice Versa: Lessons from Interpreting Counting ViTs
par: Huang, Lianghuan, et autres
Publié: (2025)

ViT Registers and Fractal ViT
par: Chou, Jason Chuan-Chih, et autres
Publié: (2026)

Enabling Efficient Hardware Acceleration of Hybrid Vision Transformer (ViT) Networks at the Edge
par: Dumoulin, Joren, et autres
Publié: (2025)

LL-ViT: Edge Deployable Vision Transformers with Look Up Table Neurons
par: Nag, Shashank, et autres
Publié: (2025)

Register and [CLS] tokens yield a decoupling of local and global features in large ViTs
par: Lappe, Alexander, et autres
Publié: (2025)

Provable Sparse Inversion and Token Relabel Enhanced One-shot Federated Learning with ViTs
par: Shen, Li, et autres
Publié: (2026)