paper-with-me

Papers

Semi-Supervised Deep Learning for Fully Convolutional Networks

2017-03-17 · Christoph Baur, Shadi Albarqouni, Nassir Navab

Deep learning usually requires large amounts of labeled training data, but annotating data is costly and tedious. The framework of semi-supervised learning provides the means to use both labeled data and arbitrary amounts of unlabeled data for training. Recently, semi-supervised deep learning has been intensively studied for standard CNN architectures. However, Fully Convolutional Networks (FCNs) set the state-of-the-art for many image segmentation tasks. To the best of our knowledge, there is no existing semi-supervised learning method for such FCNs yet. We lift the concept of auxiliary manifold embedding for semi-supervised learning to FCNs with the help of Random Feature Embedding. In our experiments on the challenging task of MS Lesion Segmentation, we leverage the proposed framework for the purpose of domain adaptation and report substantial improvements over the baseline model.

📄 PDF Abstract BibTeX arXiv:1703.06000

Code (1)

bumuckl/SemiSupervisedDLForFCNs

Tasks

Deep LearningDomain AdaptationImage SegmentationLesion SegmentationSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Hebbian Semi-Supervised Learning in a Sample Efficiency Setting

2021-03-16 · Gabriele Lagani, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato

We propose to address the issue of sample efficiency, in Deep Convolutional Neural Networks (DCNN), with a semi-supervised training strategy that combines Hebbian learning with gradient descent: all internal layers (both…

Object Recognition

Convolutional neural networks for low-resource morpheme segmentation: baseline or state-of-the-art?

2019-08-01 · WS 2019 8 · Alexey Sorokin

We apply convolutional neural networks to the task of shallow morpheme segmentation using low-resource datasets for 5 different languages. We show that both in fully supervised and semi-supervised settings our model beat…

Morphological AnalysisSegmentation

Semi-Supervised Vision Transformers

2021-11-22 · Zejia Weng, Xitong Yang, Ang Li, Zuxuan Wu 외

We study the training of Vision Transformers for semi-supervised image classification. Transformers have recently demonstrated impressive performance on a multitude of supervised learning tasks. Surprisingly, we show Vis…

image-classificationImage ClassificationInductive BiasSemi-Supervised Image Classification

Fully Linear Graph Convolutional Networks for Semi-Supervised Learning and Clustering

2021-11-15 · Yaoming Cai, Zijia Zhang, Zhihua Cai, Xiaobo Liu 외

This paper presents FLGC, a simple yet effective fully linear graph convolutional network for semi-supervised and unsupervised learning. Instead of using gradient descent, we train FLGC based on computing a global optima…

ClusteringComputational Efficiency

3D human pose estimation in video with temporal convolutions and semi-supervised training

2018-11-28 · CVPR 2019 6 · Dario Pavllo, Christoph Feichtenhofer, David Grangier, Michael Auli

In this work, we demonstrate that 3D poses in video can be effectively estimated with a fully convolutional model based on dilated temporal convolutions over 2D keypoints. We also introduce back-projection, a simple and …

3D Human Pose EstimationMonocular 3D Human Pose EstimationPose EstimationPosition+1