清华&南洋理工等提出稀疏模型反演：ViT反演加速高达3.79倍，告别无效背景！
"ViT" 相关文章
Hammering the Diagnosis: Rowhammer-Induced Stealthy Trojan Attacks on ViT-Based Medical Imaging
TransFace++: Rethinking the Face Recognition Paradigm with a Focus on Accuracy, Efficiency, and Security
Accelerating Vision Transformers with Adaptive Patch Sizes
ICCV 2025 | FDAM：告别模糊视界，源自电路理论的即插即用方法让视觉Transformer重获高清细节
ICCV 2025 | FDAM：告别模糊视界，源自电路理论的即插即用方法让视觉Transformer重获高清细节
Convolutional Neural Nets vs Vision Transformers: A SpaceNet Case Study with Balanced vs Imbalanced Regimes
Convolutional Neural Nets vs Vision Transformers: A SpaceNet Case Study with Balanced vs Imbalanced Regimes
AttriGen: Automated Multi-Attribute Annotation for Blood Cell Datasets
Transformer与ViT
⭐超越CNN与RNN：为什么Transformer是AI发展的必然选择？
DeepMind与牛津大学提出LayerLock：用渐进式层冻结实现高效、无崩溃的自监督视觉表征学习
DeepMind与牛津大学提出LayerLock：用渐进式层冻结实现高效、无崩溃的自监督视觉表征学习
EFTViT: Efficient Federated Training of Vision Transformers with Masked Images on Resource-Constrained Clients
Representation Understanding via Activation Maximization
$MV_{Hybrid}$: Improving Spatial Transcriptomics Prediction with Hybrid State Space-Vision Transformer Backbone in Pathology Vision Foundation Models
PTCMIL: Multiple Instance Learning via Prompt Token Clustering for Whole Slide Image Analysis
Post-Disaster Affected Area Segmentation with a Vision Transformer (ViT)-based EVAP Model using Sentinel-2 and Formosat-5 Imagery
Efficient Adaptation of Pre-trained Vision Transformer underpinned by Approximately Orthogonal Fine-Tuning Strategy
刚刚，三名谷歌Vision Transformer作者官宣加入OpenAI
