Related papers: InfoMatch: Entropy Neural Estimation for Semi-Supe…

Semi-Supervised Learning (SSL) has been an effective way to leverage abundant unlabeled data with extremely scarce labeled data. However, most SSL methods are commonly based on instance-wise consistency between different data…

Maximum entropy estimation is of broad interest for inferring properties of systems across many different disciplines. In this work, we significantly extend a technique we previously introduced for estimating the maximum entropy of a set of…

Due to the high cost of annotating accurate pixel-level labels, semi-supervised learning has emerged as a promising approach for cloud detection. In this paper, we propose CloudMatch, a semi-supervised framework that effectively leverages…

Active learning aims to develop label-efficient algorithms by querying the most representative samples to be labeled by a human annotator. Current active learning techniques either rely on model uncertainty to select the most uncertain…

Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model's performance. In this paper, we demonstrate the power of a simple combination of two common SSL methods: consistency regularization…

This paper introduces RankMatch, an innovative approach for Semi-Supervised Label Distribution Learning (SSLDL). Addressing the challenge of limited labeled data, RankMatch effectively utilizes a small number of labeled examples in…

Semi-supervised learning provides an expressive framework for exploiting unlabeled data when labels are insufficient. Previous semi-supervised learning methods typically match model predictions of different data-augmented views in a…

We propose a general information-theoretic approach called Seraph (SEmi-supervised metRic leArning Paradigm with Hyper-sparsity) for metric learning that does not rely upon the manifold assumption. Given the probability parameterized by a…

Deep learning techniques have greatly enhanced the performance of fire detection in videos. However, video-based fire detection models heavily rely on labeled data, and the process of data labeling is particularly costly and time-consuming,…

We propose Dense FixMatch, a simple method for online semi-supervised learning of dense and structured prediction tasks combining pseudo-labeling and consistency regularization via strong data augmentation. We enable the application of…

Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active research topic due to its key role on relaxing human supervision. In the context of image classification, recent advances to learn from…

Deep learning methodologies have been employed in several different fields, with an outstanding success in image recognition applications, such as material quality control, medical imaging, autonomous driving, etc. Deep learning models rely…

We introduce MultiMatch, a novel semi-supervised learning (SSL) algorithm combining the paradigms of co-training and consistency regularization with pseudo-labeling. At its core, MultiMatch features a pseudo-label weighting module designed…

We propose a novel method for unsupervised semantic image segmentation based on mutual information maximization between local and global high-level image features. The core idea of our work is to leverage recent progress in self-supervised…

Semi-supervised learning (SSL) has demonstrated high performance in image classification tasks by effectively utilizing both labeled and unlabeled data. However, existing SSL methods often suffer from poor calibration, with models yielding…

Establishing dense correspondences across semantically similar images remains a challenging task due to the significant intra-class variations and background clutters. Traditionally, a supervised learning was used for training the models,…

The critical challenge of Semi-Supervised Learning (SSL) is how to effectively leverage the limited labeled data and massive unlabeled data to improve the model's generalization performance. In this paper, we first revisit the popular…

A common heuristic in semi-supervised deep learning (SSDL) is to select unlabelled data based on a notion of semantic similarity to the labelled data. For example, labelled images of numbers should be paired with unlabelled images of…

The scarcity of labeled data in real-world scenarios is a critical bottleneck of deep learning's effectiveness. Semi-supervised semantic segmentation has been a typical solution to achieve a desirable tradeoff between annotation cost and…

Semi-Supervised Learning (SSL) aims to learn a model using a tiny labeled set and massive amounts of unlabeled data. To better exploit the unlabeled data the latest SSL methods use pseudo-labels predicted from a single discriminative…