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>

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/emannix/cold-paws-simclr-and-paws-semi-supervised-learning

공식 코드

Cold PAWS: Unsupervised class discovery and addressing the cold-start problem for semi-supervised learning

https://github.com/erjui/DHO

공식 코드

Simple Semi-supervised Knowledge Distillation from Vision-Language Models via $\mathbf{\texttt{D}}$ual-$\mathbf{\texttt{H}}$ead $\mathbf{\texttt{O}}$ptimization

https://github.com/facebookresearch/barlowtwins

공식 코드

Barlow Twins: Self-Supervised Learning via Redundancy Reduction

https://github.com/facebookresearch/irmae

공식 코드

Implicit Rank-Minimizing Autoencoder

https://github.com/facebookresearch/mixup-cifar10

공식 코드

mixup: Beyond Empirical Risk Minimization

https://github.com/facebookresearch/msn

공식 코드

Masked Siamese Networks for Label-Efficient Learning

https://github.com/facebookresearch/suncet

공식 코드

Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples

https://github.com/facebookresearch/swav

공식 코드

Unsupervised Learning of Visual Features by Contrasting Cluster Assignments

https://github.com/facebookresearch/vicreg

공식 코드

VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning

https://github.com/facebookresearch/vissl

공식 코드

Self-supervised Pretraining of Visual Features in the Wild

https://github.com/frank-xwang/CLD-UnsupervisedLearning

공식 코드

Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination

https://github.com/frank-xwang/debiased-pseudo-labeling

공식 코드

Debiased Learning from Naturally Imbalanced Pseudo-Labels

https://github.com/giakoumoglou/synco

공식 코드

SynCo: Synthetic Hard Negatives in Contrastive Learning for Better Unsupervised Visual Representations

https://github.com/gimme1dollar/gradcam-consistency-semi-sup

공식 코드

Semi-supervised Image Classification with Grad-CAM Consistency

https://github.com/google-deepmind/relicv2

공식 코드

Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?

https://github.com/google-research/fixmatch

공식 코드

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

https://github.com/google-research/fnc

공식 코드

Boosting Contrastive Self-Supervised Learning with False Negative Cancellation

https://github.com/google-research/google-research

공식 코드

Milking CowMask for Semi-Supervised Image Classification

https://github.com/google-research/google-research/tree/master/meta_pseudo_labels

공식 코드

Meta Pseudo Labels

https://github.com/google-research/mixmatch

공식 코드

MixMatch: A Holistic Approach to Semi-Supervised Learning

https://github.com/google-research/remixmatch

공식 코드

ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring

https://github.com/google-research/simclr

공식 코드

A Simple Framework for Contrastive Learning of Visual Representations

https://github.com/google-research/uda

공식 코드

Unsupervised Data Augmentation for Consistency Training

https://github.com/grasp-lyrl/deep_reference_priors

공식 코드

Deep Reference Priors: What is the best way to pretrain a model?

https://github.com/islam-nassar/semco

공식 코드

All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training

https://github.com/izmailovpavel/flowgmm

공식 코드

Semi-Supervised Learning with Normalizing Flows

https://github.com/jaeill/CVPR23-VNE

공식 코드

VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution

https://github.com/jayrothenberger/meta-co-training

공식 코드

Meta Co-Training: Two Views are Better than One

https://github.com/jianf-wang/np-match

공식 코드

NP-Match: When Neural Processes meet Semi-Supervised Learning

https://github.com/jianf-wang/np-semiseg

공식 코드

NP-SemiSeg: When Neural Processes meet Semi-Supervised Semantic Segmentation

https://github.com/kimiyoung/ssl_bad_gan

공식 코드

Good Semi-supervised Learning that Requires a Bad GAN

https://github.com/kunzhan/infomatch

공식 코드

InfoMatch: Entropy Neural Estimation for Semi-Supervised Image Classification

https://github.com/kylezheng1997/simmatch

공식 코드

SimMatch: Semi-supervised Learning with Similarity Matching

https://github.com/layumi/AdaBoost_Seg

공식 코드

Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation

https://github.com/layumi/Cifar10-Adaboost

공식 코드

Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation

https://github.com/ljjcoder/PCL

공식 코드

Probabilistic Contrastive Learning for Domain Adaptation

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.