Semi-supervised image classification leverages unlabelled data as well as labelled data to increase classification performance.
|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
We present a variety of new architectural features and training procedures that we apply to the generative adversarial networks (GANs) framework.
#6 best model for Semi-Supervised Image Classification on SVHN, 1000 labels
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 Image Classification on CIFAR-10
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, 1000 labels
When trained with 10% of the labeled set, UDA improves the top-1/top-5 accuracy from 55. 1/77. 3% to 68. 7/88. 5%.
Semi-supervised learning has proven to be a powerful paradigm for leveraging unlabeled data to mitigate the reliance on large labeled datasets.
SOTA for Image Classification on STL-10
In our experiments, we applied VAT to supervised and semi-supervised learning tasks on multiple benchmark datasets.
#2 best model for Semi-Supervised Image Classification on SVHN, 1000 labels
Convolutional neural networks are capable of learning powerful representational spaces, which are necessary for tackling complex learning tasks.
#2 best model for Image Classification on SVHN
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 learning methods based on generative adversarial networks (GANs) obtained strong empirical results, but it is not clear 1) how the discriminator benefits from joint training with a generator, and 2) why good semi-supervised classification performance and a good generator cannot be obtained at the same time.
#8 best model for Semi-Supervised Image Classification on CIFAR-10, 4000 Labels