paper-with-me

홈 › Papers

Interpolation Consistency Training for Semi-Supervised Learning

2019-03-09 · Vikas Verma, Kenji Kawaguchi, Alex Lamb, Juho Kannala, Arno Solin, Yoshua Bengio, David Lopez-Paz

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.

📄 PDF Abstract BibTeX arXiv:1903.03825

Code (4)

vikasverma1077/ICT 공식 구현 pytorch
kevinghst/ICT pytorch
perrying/realistic-ssl-evaluation-pytorch pytorch
yanzhicong/mixup_ssl pytorch

Tasks

General ClassificationSemi-Supervised Image Classification

Similar Papers 제목 키워드 기반

Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training

2022-06-17 · CVPR 2022 1 · Xiao Lu, Yihong Cao, Sheng Liu, Chengjiang Long 외

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 Detection

An Embarrassingly Simple Consistency Regularization Method for Semi-Supervised Medical Image Segmentation

2022-02-01 · Hritam Basak, Rajarshi Bhattacharya, Rukhshanda Hussain, Agniv Chatterjee

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+2

MCICSAM: Monte Carlo-guided Interpolation Consistency Segment Anything Model for Semi-Supervised Prostate Zone Segmentation

2024-09-20 · Guantian Huang, Beibei Li, Xiaobing Fan, Aritrick Chatterjee 외

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 Segmentation

Distributed Semi-supervised Fuzzy Regression with Interpolation Consistency Regularization

2022-09-18 · Ye Shi, Leijie Zhang, Zehong Cao, M. Tanveer 외

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 …

regression

Consistency Regularization with Generative Adversarial Networks for Semi-Supervised Learning

2020-07-08 · Zexi Chen, Bharathkumar Ramachandra, Ranga Raju Vatsavai

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