Related papers: PseudoMapTrainer: Learning Online Mapping without …

High-definition (HD) maps offer extensive and accurate environmental information about the driving scene, making them a crucial and essential element for planning within autonomous driving systems. To avoid extensive efforts from manual…

Semi-supervised multi-organ medical image segmentation aids physicians in improving disease diagnosis and treatment planning and reduces the time and effort required for organ annotation.Existing state-of-the-art methods train the labeled…

We present Self Meta Pseudo Labels, a novel semi-supervised learning method similar to Meta Pseudo Labels but without the teacher model. We introduce a novel way to use a single model for both generating pseudo labels and classification,…

We present SDTracker, a method that harnesses the potential of synthetic data for multi-object tracking of real-world scenes in a domain generalization and semi-supervised fashion. First, we use the ImageNet dataset as an auxiliary to…

We present a novel data-efficient semi-supervised framework to improve the generalization of image captioning models. Constructing a large-scale labeled image captioning dataset is an expensive task in terms of labor, time, and cost. In…

Dataset pruning reduces the storage and training costs of deep learning by selecting an informative subset from a large dataset. However, most existing pruning methods require fully labeled data, which limits their applicability in…

Estimating building footprint maps from geospatial data is of paramount importance in urban planning, development, disaster management, and various other applications. Deep learning methodologies have gained prominence in building…

This work proposes a hybrid unsupervised and supervised learning method to pre-train models applied in Earth observation downstream tasks when only a handful of labels denoting very general semantic concepts are available. We combine a…

Deep-learning metrics have recently demonstrated extremely good performance to match image patches for stereo reconstruction. However, training such metrics requires large amount of labeled stereo images, which can be difficult or costly to…

Pseudo-supervised learning methods have been shown to be effective for weakly supervised object localization tasks. However, the effectiveness depends on the powerful regularization ability of deep neural networks. Based on the assumption…

Medical ultrasound imaging is ubiquitous, but manual analysis struggles to keep pace. Automated segmentation can help but requires large labeled datasets, which are scarce. Semi-supervised learning leveraging both unlabeled and limited…

Deep neural networks for aerial image segmentation require large amounts of labeled data, but high-quality aerial datasets with precise annotations are scarce and costly to produce. To address this limitation, we propose a self-supervised…

Despite the significant progress that depth-based 3D hand pose estimation methods have made in recent years, they still require a large amount of labeled training data to achieve high accuracy. However, collecting such data is both costly…

This paper proposes a novel pseudo-labeling method for medical image segmentation that can perform learning on ``individual images'' to select effective pseudo-labels. We introduce Positive and Unlabeled Learning (PU learning), which uses…

The primary objective of this work is to present an alternative approach aimed at reducing the dependency on labeled data. Our proposed method involves utilizing autoencoder pre-training within a face image recognition task with two step…

Pseudo-labelling is a popular technique in unsuper-vised domain adaptation for semantic segmentation. However, pseudo labels are noisy and inevitably have confirmation bias due to the discrepancy between source and target domains and…

Unsupervised pre-training was a critical technique for training deep neural networks years ago. With sufficient labeled data and modern training techniques, it is possible to train very deep neural networks from scratch in a purely…

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,…

Pseudo-labeling is a crucial technique in semi-supervised learning (SSL), where artificial labels are generated for unlabeled data by a trained model, allowing for the simultaneous training of labeled and unlabeled data in a supervised…

Video recognition models have progressed significantly over the past few years, evolving from shallow classifiers trained on hand-crafted features to deep spatiotemporal networks. However, labeled video data required to train such models…