Semi-Supervised Image Classification
Semi-supervised image classification leverages unlabelled data as well as labelled data to increase classification performance.
( Image credit: Self-Supervised Semi-Supervised Learning )
Leaderboards
| TREND | DATASET | BEST METHOD | PAPER TITLE | PAPER | CODE | COMPARE |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
Greatest papers with code
Improved Techniques for Training GANs
NeurIPS 2016
• tensorflow/models
• 
We present a variety of new architectural features and training procedures that we apply to the generative adversarial networks (GANs) framework.
#8 best model for
Conditional Image Generation
on CIFAR-10
CONDITIONAL IMAGE GENERATION SEMI-SUPERVISED IMAGE CLASSIFICATION
Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks
We introduce a simple semi-supervised learning approach for images based on in-painting using an adversarial loss.
#4 best model for
Semi-Supervised Image Classification
on STL-10, 1000 Labels
mixup: Beyond Empirical Risk Minimization
ICLR 2018
• rwightman/pytorch-image-models
• 
We also find that mixup reduces the memorization of corrupt labels, increases the robustness to adversarial examples, and stabilizes the training of generative adversarial networks.
#6 best model for
Semi-Supervised Image Classification
on cifar10, 250 Labels
Unsupervised Data Augmentation for Consistency Training
arXiv 2019
• google-research/uda
•
In this work, we present a new perspective on how to effectively noise unlabeled examples and argue that the quality of noising, specifically those produced by advanced data augmentation methods, plays a crucial role in semi-supervised learning.
IMAGE AUGMENTATION SEMI-SUPERVISED IMAGE CLASSIFICATION TEXT CLASSIFICATION TRANSFER LEARNING
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
NeurIPS 2017
• CuriousAI/mean-teacher
•
Without changing the network architecture, Mean Teacher achieves an error rate of 4. 35% on SVHN with 250 labels, outperforming Temporal Ensembling trained with 1000 labels.
#3 best model for
Semi-Supervised Image Classification
on SVHN, 250 Labels
MixMatch: A Holistic Approach to Semi-Supervised Learning
NeurIPS 2019
• google-research/mixmatch
•
Semi-supervised learning has proven to be a powerful paradigm for leveraging unlabeled data to mitigate the reliance on large labeled datasets.
#2 best model for
Image Classification
on STL-10
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
• tensorflow/neural-structured-learning
•
In our experiments, we applied VAT to supervised and semi-supervised learning tasks on multiple benchmark datasets.
#4 best model for
Semi-Supervised Image Classification
on SVHN, 1000 labels
Semi-Supervised Learning with Ladder Networks
We combine supervised learning with unsupervised learning in deep neural networks.
#13 best model for
Semi-Supervised Image Classification
on CIFAR-10, 4000 Labels
Invariant Information Clustering for Unsupervised Image Classification and Segmentation
arXiv 2019
• xu-ji/IIC
•
The method is not specialised to computer vision and operates on any paired dataset samples; in our experiments we use random transforms to obtain a pair from each image.
SEMI-SUPERVISED IMAGE CLASSIFICATION UNSUPERVISED IMAGE CLASSIFICATION UNSUPERVISED SEMANTIC SEGMENTATION
Improved Regularization of Convolutional Neural Networks with Cutout
Convolutional neural networks are capable of learning powerful representational spaces, which are necessary for tackling complex learning tasks.
#3 best model for
Image Classification
on SVHN