Papers with Code 아카이브
Semi-Supervised Image Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 59
- 보존된 평가 기록
- 456
Semi-supervised image classification leverages unlabelled data as well as labelled data to increase classification performance.
You may want to read some blog posts to get an overview before reading the papers and checking the leaderboards:
- An overview of proxy-label approaches for semi-supervised learning - Sebastian Ruder
- Semi-Supervised Learning in Computer Vision - Amit Chaudhary
<span style="color:grey; opacity: 0.6">( Image credit: Self-Supervised Semi-Supervised Learning )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learning
FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning
Improving Face Recognition by Clustering Unlabeled Faces in the Wild
Temporal Self-Ensembling Teacher for Semi-Supervised Object Detection
Consistency Regularization with Generative Adversarial Networks for Semi-Supervised Learning
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
Big Self-Supervised Models are Strong Semi-Supervised Learners
Building One-Shot Semi-supervised (BOSS) Learning up to Fully Supervised Performance
Bootstrap your own latent: A new approach to self-supervised Learning
SCAN: Learning to Classify Images without Labels
A Self-ensembling Framework for Semi-supervised Knee Cartilage Defects Assessment with Dual-Consistency
Prototypical Contrastive Learning of Unsupervised Representations
DMT: Dynamic Mutual Training for Semi-Supervised Learning
Milking CowMask for Semi-Supervised Image Classification
Meta Pseudo Labels
A Simple Framework for Contrastive Learning of Visual Representations
Subspace Capsule Network
batchboost: regularization for stabilizing training with resistance to underfitting & overfitting
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
Semi-Supervised Learning with Normalizing Flows
SESS: Self-Ensembling Semi-Supervised 3D Object Detection
Triple Generative Adversarial Networks
RealMix: Towards Realistic Semi-Supervised Deep Learning Algorithms
Self-Supervised Learning of Pretext-Invariant Representations
Flow Contrastive Estimation of Energy-Based Models
EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble Transformations
ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring
Adversarial Transformations for Semi-Supervised Learning
Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning
Repetitive Reprediction Deep Decipher for Semi-Supervised Learning
Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation
Large Scale Adversarial Representation Learning
Exploring Self-Supervised Regularization for Supervised and Semi-Supervised Learning
Energy Models for Better Pseudo-Labels: Improving Semi-Supervised Classification with the 1-Laplacian Graph Energy
Manifold Graph with Learned Prototypes for Semi-Supervised Image Classification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.