Interpolation Consistency Training for Semi-Supervised Learning
We introduce Interpolation Consistency Training (ICT), a simple and computation efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm. ICT encourages the prediction at an interpolation of unlabeled points to be consistent with the interpolation of the predictions at those points. In classification problems, ICT moves the decision boundary to low-density regions of the data distribution. Our experiments show that ICT achieves state-of-the-art performance when applied to standard neural network architectures on the CIFAR-10 and SVHN benchmark datasets. Our theoretical analysis shows that ICT corresponds to a certain type of data-adaptive regularization with unlabeled points which reduces overfitting to labeled points under high confidence values.
Code (4)
Tasks
General ClassificationSemi-Supervised Image ClassificationSimilar Papers 제목 키워드 기반
Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training
It is challenging to annotate large-scale datasets for supervised video shadow detection methods. Using a model trained on labeled images to the video frames directly may lead to high generalization error and temporal in…
Shadow DetectionSpatial InterpolationVideo Shadow DetectionAn Embarrassingly Simple Consistency Regularization Method for Semi-Supervised Medical Image Segmentation
The scarcity of pixel-level annotation is a prevalent problem in medical image segmentation tasks. In this paper, we introduce a novel regularization strategy involving interpolation-based mixing for semi-supervised medi…
3D Medical Imaging SegmentationImage SegmentationMedical Image SegmentationSegmentation+2MCICSAM: Monte Carlo-guided Interpolation Consistency Segment Anything Model for Semi-Supervised Prostate Zone Segmentation
Accurate segmentation of various regions within the prostate is pivotal for diagnosing and treating prostate-related diseases. However, the scarcity of labeled data, particularly in specialized medical fields like prosta…
Image SegmentationSegmentationSemantic SegmentationDistributed Semi-supervised Fuzzy Regression with Interpolation Consistency Regularization
Recently, distributed semi-supervised learning (DSSL) algorithms have shown their effectiveness in leveraging unlabeled samples over interconnected networks, where agents cannot share their original data with each other …
regressionConsistency Regularization with Generative Adversarial Networks for Semi-Supervised Learning
Generative Adversarial Networks (GANs) based semi-supervised learning (SSL) approaches are shown to improve classification performance by utilizing a large number of unlabeled samples in conjunction with limited labeled …
image-classificationImage ClassificationSemi-Supervised Image Classification