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 leaderboard:
( Image credit: Self-Supervised Semi-Supervised Learning )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Our experiments show that this new composite consistency regularization based semi-GAN significantly improves its performance and achieves new state-of-the-art performance among GAN-based SSL approaches.
In addition, we also propose a new data augmentation strategy, multi-crop, that uses a mix of views with different resolutions in place of two full-resolution views, without increasing the memory or compute requirements much.
#4 best model for Self-Supervised Image Classification on ImageNet
The performance of existing point cloud-based 3D object detection methods heavily relies on large-scale high-quality 3D annotations.
This paper presents Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that addresses the fundamental limitations of instance-wise contrastive learning.
#15 best model for Semi-Supervised Image Classification on ImageNet - 1% labeled data (Top 5 Accuracy metric)
Human observers can learn to recognize new categories of objects from a handful of examples, yet doing so with machine perception remains an open challenge.
#14 best model for Semi-Supervised Image Classification on ImageNet - 1% labeled data
We propose a Regularization framework based on Adversarial Transformations (RAT) for semi-supervised learning.
We consider statistical models of estimation of a rank-one matrix (the spike) corrupted by an additive gaussian noise matrix in the sparse limit.
#3 best model for Nested Named Entity Recognition on ACE 2005
To learn target discriminative representations, using pseudo-labels is a simple yet effective approach for unsupervised domain adaptation.
We then show that when combined with these regularizers, the proposed method facilitates the propagation of information from generated prototypes to image data to further improve results.