https://github.com/JoonHyung-Park/SimCLR
A Simple Framework for Contrastive Learning of Visual Representations
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/JunweiLiang/Object_Detection_Tracking
https://github.com/KaiyangZhou/ssdg-benchmark
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
https://github.com/Kaushalya/medclip
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/Kennethborup/BYOL
Bootstrap your own latent: A new approach to self-supervised Learning
https://github.com/KentaItakura/CNN-classification-using-random-erasing-and-cut-out
Improved Regularization of Convolutional Neural Networks with Cutout
https://github.com/Kyan-Ge/Semi-supervised-Gan
https://github.com/LEGO999/BIgBiGAN
https://github.com/LEGO999/BigBiGAN-TensorFlow2.0
https://github.com/LKLQQ/ssc_resnet50
CoMatch: Semi-supervised Learning with Contrastive Graph Regularization
https://github.com/LMaxence/Cifar10_Classification
Improved Regularization of Convolutional Neural Networks with Cutout
https://github.com/LYWH/oppo_face_vat
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
https://github.com/Lan1991Xu/ONE_NeurIPS2018
https://github.com/LeeDoYup/FixMatch-pytorch
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
https://github.com/LeiLiu-byte/the-Essence-of-LT-Rocognition
https://github.com/Linear95/CLUB
https://github.com/Liut2016/ecg-supcontrast
A Simple Framework for Contrastive Learning of Visual Representations
https://github.com/LsAntonio/60daysofudacity
https://github.com/MaxLikesMath/Barlow-Twins-Pytorch
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Improved_Techniques_for_Training_GANs
https://github.com/Mayurji/SimCLR
A Simple Framework for Contrastive Learning of Visual Representations
https://github.com/Medabid1/CPC
https://github.com/Mind23-2/MindCode-76
A Simple Framework for Contrastive Learning of Visual Representations
https://github.com/MindCode-4/code-4/tree/main/rag
RealMix: Towards Realistic Semi-Supervised Deep Learning Algorithms
https://github.com/MindSpore-scientific-2/code-12/tree/main/GAN-master
https://github.com/Mixture-of-Rookie/PASSL
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
https://github.com/NYU-DICE-Lab/open_clip
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/Namkyeong/BGRL_Pytorch
Bootstrap your own latent: A new approach to self-supervised Learning
https://github.com/NaturalHistoryMuseum/semantic-segmentation
https://github.com/Nirvan101/Image-Restoration-deep-learning
Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks
https://github.com/OFRIN/Tensorflow_FixMatch
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
https://github.com/OFRIN/Tensorflow_MixUp
https://github.com/OML-Team/open-metric-learning
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/P2333/Mixup-Inference
https://github.com/PaddlePaddle/PASSL
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
https://github.com/PaddlePaddle/PASSL/blob/main/docs/Train_BYOL_model.md
Bootstrap your own latent: A new approach to self-supervised Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.