Related papers: Revisiting consistency for semi-supervised semanti…
Consistency regularization on label predictions becomes a fundamental technique in semi-supervised learning, but it still requires a large number of training iterations for high performance. In this study, we analyze that the consistency…
Deep networks are successfully used as classification models yielding state-of-the-art results when trained on a large number of labeled samples. These models, however, are usually much less suited for semi-supervised problems because of…
In semantic segmentation, the creation of pixel-level labels for training data incurs significant costs. To address this problem, semi-supervised learning, which utilizes a small number of labeled images alongside unlabeled images to…
Deep co-training has recently been proposed as an effective approach for image segmentation when annotated data is scarce. In this paper, we improve existing approaches for semi-supervised segmentation with a self-paced and self-consistent…
We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and…
In this work, we used a semi-supervised learning method to train deep learning model that can segment the brain MRI images. The semi-supervised model uses less labeled data, and the performance is competitive with the supervised model with…
We bring a new perspective to semi-supervised semantic segmentation by providing an analysis on the labeled and unlabeled distributions in training datasets. We first figure out that the distribution gap between labeled and unlabeled…
Convolutional neural networks (CNNs) have been successfully applied to solve the problem of correspondence estimation between semantically related images. Due to non-availability of large training datasets, existing methods resort to…
In this work, we propose a simple yet effective meta-learning algorithm in semi-supervised learning. We notice that most existing consistency-based approaches suffer from overfitting and limited model generalization ability, especially when…
Semi-supervised learning (SSL) can reduce the need for large labelled datasets by incorporating unlabelled data into the training. This is particularly interesting for semantic segmentation, where labelling data is very costly and…
In response to the growing demand for 3D object detection in applications such as autonomous driving, robotics, and augmented reality, this work focuses on the evaluation of semi-supervised learning approaches for point cloud data. The…
This paper presents a semi-supervised learning framework that is new in being designed for automatic modulation classification (AMC). By carefully utilizing unlabeled signal data with a self-supervised contrastive-learning pre-training…
Traditional supervised medical image segmentation models require large amounts of labeled data for training; however, obtaining such large-scale labeled datasets in the real world is extremely challenging. Recent semi-supervised…
We present a novel self-taught framework for unsupervised metric learning, which alternates between predicting class-equivalence relations between data through a moving average of an embedding model and learning the model with the predicted…
Effective convolutional neural networks are trained on large sets of labeled data. However, creating large labeled datasets is a very costly and time-consuming task. Semi-supervised learning uses unlabeled data to train a model with higher…
Hyperspectral image (HSI) classification is gaining a lot of momentum in present time because of high inherent spectral information within the images. However, these images suffer from the problem of curse of dimensionality and usually…
Due to abundance of data from multiple modalities, cross-modal retrieval tasks with image-text, audio-image, etc. are gaining increasing importance. Of the different approaches proposed, supervised methods usually give significant…
Consistency learning using input image, feature, or network perturbations has shown remarkable results in semi-supervised semantic segmentation, but this approach can be seriously affected by inaccurate predictions of unlabelled training…
Pre-training a recognition model with contrastive learning on a large dataset of unlabeled data has shown great potential to boost the performance of a downstream task, e.g., image classification. However, in domains such as medical…
Despite significant advances, the performance of state-of-the-art continual learning approaches hinges on the unrealistic scenario of fully labeled data. In this paper, we tackle this challenge and propose an approach for continual…