← Efficient ViTs

Papers with Code · CC BY-SA 4.0

ImageNet-1K (With LV-ViT-S)

아카이브 평가 19건 · 마지막 적재/변경 2026-10-30

원본 데이터셋 링크 1

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
MCTF ($r=8$)	Top 1 Accuracy 83.5 GFLOPs 4.9	Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers 2024-03-15	코드 1
MCTF ($r=12$)	Top 1 Accuracy 83.4 GFLOPs 4.2	Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers 2024-03-15	코드 1
Base (LV-ViT-S)	Top 1 Accuracy 83.3 GFLOPs 6.6	All Tokens Matter: Token Labeling for Training Better Vision Transformers 2021-04-22	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7
DynamicViT (90%)	Top 1 Accuracy 83.3 GFLOPs 5.8	DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification 2021-06-03	코드 1 · 코드 2
DynamicViT (80%)	Top 1 Accuracy 83.2 GFLOPs 5.1	DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification 2021-06-03	코드 1 · 코드 2
BAT	Top 1 Accuracy 83.1 GFLOPs 4.7	Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers 2022-11-21	코드 1
AS-LV-S (70%)	Top 1 Accuracy 83.1 GFLOPs 4.6	Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention 2022-09-28	코드 1
PPT	Top 1 Accuracy 83.1 GFLOPs 4.6	PPT: Token Pruning and Pooling for Efficient Vision Transformers 2023-10-03	코드 1 · 코드 2
SPViT	Top 1 Accuracy 83.1 GFLOPs 4.3	SPViT: Enabling Faster Vision Transformers via Soft Token Pruning 2021-12-27	코드 1
EViT (70%)	Top 1 Accuracy 83.0 GFLOPs 4.7	Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations 2022-02-16	코드 1 · 코드 2
DynamicViT (70%)	Top 1 Accuracy 83.0 GFLOPs 4.6	DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification 2021-06-03	코드 1 · 코드 2
DPS-LV-ViT-S	Top 1 Accuracy 82.9 GFLOPs 4.5	Patch Slimming for Efficient Vision Transformers 2021-06-05	연결 없음
DiffRate	Top 1 Accuracy 82.6 GFLOPs 3.9	DiffRate : Differentiable Compression Rate for Efficient Vision Transformers 2023-05-29	코드 1
AS-LV-S (60%)	Top 1 Accuracy 82.6 GFLOPs 3.9	Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention 2022-09-28	코드 1
dTPS	Top 1 Accuracy 82.6 GFLOPs 3.8	Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers 2023-04-21	코드 1
EViT (50%)	Top 1 Accuracy 82.5 GFLOPs 3.9	Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations 2022-02-16	코드 1 · 코드 2
eTPS	Top 1 Accuracy 82.5 GFLOPs 3.8	Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers 2023-04-21	코드 1
PS-LV-ViT-S	Top 1 Accuracy 82.4 GFLOPs 4.7	Patch Slimming for Efficient Vision Transformers 2021-06-05	연결 없음
MCTF ($r=16$)	Top 1 Accuracy 82.3 GFLOPs 3.6	Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers 2024-03-15	코드 1