Papers with Code 아카이브
Efficient ViTs
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 3
- 보존된 평가 기록
- 82
Increasing the efficiency of ViTs without the modification of the architecture. (i.e., Key & Query Sparsification, Token pruning & merging)
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
M$^2$-ViT: Accelerating Hybrid Vision Transformers with Two-Level Mixed Quantization
Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision Transformer
An FPGA-Based Reconfigurable Accelerator for Convolution-Transformer Hybrid EfficientViT
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers
GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation
PPT: Token Pruning and Pooling for Efficient Vision Transformers
Learned Thresholds Token Merging and Pruning for Vision Transformers
MDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation Datasets
ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer
DiffRate : Differentiable Compression Rate for Efficient Vision Transformers
Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers
Making Vision Transformers Efficient from A Token Sparsification View
Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers
Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference
Token Merging: Your ViT But Faster
Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention
Fast Vision Transformers with HiLo Attention
Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations
SPViT: Enabling Faster Vision Transformers via Soft Token Pruning
AdaViT: Adaptive Tokens for Efficient Vision Transformer
Adaptive Token Sampling For Efficient Vision Transformers
Pruning Self-attentions into Convolutional Layers in Single Path
Global Vision Transformer Pruning with Hessian-Aware Saliency
Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer
IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers
Chasing Sparsity in Vision Transformers: An End-to-End Exploration
Patch Slimming for Efficient Vision Transformers
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
All Tokens Matter: Token Labeling for Training Better Vision Transformers
Scalable Vision Transformers with Hierarchical Pooling
Training data-efficient image transformers & distillation through attention
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.