SOTAVerified

Efficient ViTs

Increasing the efficiency of ViTs without the modification of the architecture. (i.e., Key & Query Sparsification, Token pruning & merging)

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 32 papers

TitleStatusHype
Token Merging: Your ViT But FasterCode3
Fast Vision Transformers with HiLo AttentionCode2
Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-AttentionCode1
Adaptive Token Sampling For Efficient Vision TransformersCode1
AdaViT: Adaptive Tokens for Efficient Vision TransformerCode1
Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer InferenceCode1
Chasing Sparsity in Vision Transformers: An End-to-End ExplorationCode1
DiffRate : Differentiable Compression Rate for Efficient Vision TransformersCode1
DynamicViT: Efficient Vision Transformers with Dynamic Token SparsificationCode1
Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision TransformerCode1
GTP-ViT: Efficient Vision Transformers via Graph-based Token PropagationCode1
Training data-efficient image transformers & distillation through attentionCode1
Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision TransformersCode1
Learned Thresholds Token Merging and Pruning for Vision TransformersCode1
All Tokens Matter: Token Labeling for Training Better Vision TransformersCode1
Making Vision Transformers Efficient from A Token Sparsification ViewCode1
MDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation DatasetsCode1
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision TransformersCode1
Not All Patches are What You Need: Expediting Vision Transformers via Token ReorganizationsCode1
Global Vision Transformer Pruning with Hessian-Aware SaliencyCode1
SPViT: Enabling Faster Vision Transformers via Soft Token PruningCode1
PPT: Token Pruning and Pooling for Efficient Vision TransformersCode1
Scalable Vision Transformers with Hierarchical PoolingCode1
Pruning Self-attentions into Convolutional Layers in Single PathCode1
ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision TransformerCode1
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.