Papers with Code · CC BY-SA 4.0

ImageNet - 10% labeled data

아카이브 평가 75건 · 마지막 적재/변경 2026-10-30

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
DHO (ViT-Large)	Top 1 Accuracy 85.9%	Simple Semi-supervised Knowledge Distillation from Vision-Language Models via $\mathbf{\texttt{D}}$ual-$\mathbf{\texttt{H}}$ead $\mathbf{\texttt{O}}$ptimization 2025-05-12	코드 1
Meta Co-Training	Top 1 Accuracy 85.8%	Meta Co-Training: Two Views are Better than One 2023-11-29	코드 1
REACT (ViT-Large)	Top 1 Accuracy 85.1%	Learning Customized Visual Models with Retrieval-Augmented Knowledge 2023-01-17	코드 1
Semi-SST (ViT-Huge)	Top 1 Accuracy 84.9%	SST: Self-training with Self-adaptive Thresholding for Semi-supervised Learning 2025-05-31	연결 없음
Super-SST (ViT-Huge)	Top 1 Accuracy 84.8%	SST: Self-training with Self-adaptive Thresholding for Semi-supervised Learning 2025-05-31	연결 없음
Semi-ViT (ViT-Huge)	Top 5 Accuracy 96.6% Top 1 Accuracy 84.3%	Semi-supervised Vision Transformers at Scale 2022-08-11	코드 1
Semi-ViT (ViT-Large)	Top 1 Accuracy 83.3%	Semi-supervised Vision Transformers at Scale 2022-08-11	코드 1
DHO (ViT-Base)	Top 1 Accuracy 82.8%	Simple Semi-supervised Knowledge Distillation from Vision-Language Models via $\mathbf{\texttt{D}}$ual-$\mathbf{\texttt{H}}$ead $\mathbf{\texttt{O}}$ptimization 2025-05-12	코드 1
SimCLRv2 self-distilled (ResNet-152 x3, SK)	Top 5 Accuracy 95.5% Top 1 Accuracy 80.9%	Big Self-Supervised Models are Strong Semi-Supervised Learners 2020-06-17	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9
Super-SST (ViT-Small distilled)	Top 1 Accuracy 80.3%	SST: Self-training with Self-adaptive Thresholding for Semi-supervised Learning 2025-05-31	연결 없음
SimCLRv2 distilled (ResNet-50 x2, SK)	Top 5 Accuracy 95.0% Top 1 Accuracy 80.2%	Big Self-Supervised Models are Strong Semi-Supervised Learners 2020-06-17	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9
SimCLRv2 (ResNet-152 x3, SK)	Top 5 Accuracy 95.0% Top 1 Accuracy 80.1%	Big Self-Supervised Models are Strong Semi-Supervised Learners 2020-06-17	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9
Semi-ViT (ViT-Base)	Top 1 Accuracy 79.7%	Semi-supervised Vision Transformers at Scale 2022-08-11	코드 1
PAWS (ResNet-50 4x)	Top 1 Accuracy 79.0%	Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples 2021-04-28	코드 1 · 코드 2 · 코드 3 · 코드 4
SEER (RegNet10B)	Top 1 Accuracy 78.8%	Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision 2022-02-16	코드 1
Semi-SST (ViT-Small)	Top 1 Accuracy 78.6%	SST: Self-training with Self-adaptive Thresholding for Semi-supervised Learning 2025-05-31	연결 없음
Super-SST (ViT-Small)	Top 1 Accuracy 78.3%	SST: Self-training with Self-adaptive Thresholding for Semi-supervised Learning 2025-05-31	연결 없음
SEER Large (RegNetY-256GF)	Top 1 Accuracy 77.9%	Self-supervised Pretraining of Visual Features in the Wild 2021-03-02	코드 1
PAWS (ResNet-50 2x)	Top 1 Accuracy 77.8%	Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples 2021-04-28	코드 1 · 코드 2 · 코드 3 · 코드 4
SimCLRv2 distilled (ResNet-50)	Top 5 Accuracy 93.4% Top 1 Accuracy 77.5%	Big Self-Supervised Models are Strong Semi-Supervised Learners 2020-06-17	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9
Semi-ViT (ViT-Small)	Top 1 Accuracy 77.1%	Semi-supervised Vision Transformers at Scale 2022-08-11	코드 1
SEER Small (RegNetY-128GF)	Top 1 Accuracy 76.7%	Self-supervised Pretraining of Visual Features in the Wild 2021-03-02	코드 1
SimMatchV2 (ResNet-50)	Top 1 Accuracy 76.2%	SimMatchV2: Semi-Supervised Learning with Graph Consistency 2023-08-13	코드 1 · 코드 2
Semiformer (ViT-S + Conv)	Top 1 Accuracy 75.5%	Semi-Supervised Vision Transformers 2021-11-22	코드 1
PAWS (ResNet-50)	Top 1 Accuracy 75.5%	Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples 2021-04-28	코드 1 · 코드 2 · 코드 3 · 코드 4
TWIST (ResNet-50 x2)	Top 5 Accuracy 92.8% Top 1 Accuracy 75.3%	Self-Supervised Learning by Estimating Twin Class Distributions 2021-10-14	코드 1 · 코드 2
SimMatch + EPASS (ResNet-50)	Top 5 Accuracy 92.6 Top 1 Accuracy 75.3%	Debiasing, calibrating, and improving Semi-supervised Learning performance via simple Ensemble Projector 2023-10-24	코드 1
SequenceMatch (ResNet-50)	Top 5 Accuracy 91.9 Top 1 Accuracy 75.2%	SequenceMatch: Revisiting the design of weak-strong augmentations for Semi-supervised learning 2023-10-24	코드 1
SimMatch (ResNet-50)	Top 1 Accuracy 74.4%	SimMatch: Semi-supervised Learning with Similarity Matching 2022-03-14	코드 1
CoMatch + EPASS (ResNet-50)	Top 5 Accuracy 91.5 Top 1 Accuracy 74.1%	Debiasing, calibrating, and improving Semi-supervised Learning performance via simple Ensemble Projector 2023-10-24	코드 1