Related papers: Simulation-Based Pretraining and Domain Adaptation…
Constraint-based learning reduces the burden of collecting labels by having users specify general properties of structured outputs, such as constraints imposed by physical laws. We propose a novel framework for simultaneously learning these…
Performance of a pre-trained semantic segmentation model is likely to substantially decrease on data from a new domain. We show a pre-trained model can be adapted to unlabelled target domain data by calculating soft-label prototypes under…
Deep learning-based weather prediction models have advanced significantly in recent years. However, data-driven models based on deep learning are difficult to apply to real-world applications because they are vulnerable to spatial-temporal…
We present an approach to domain adaptation, addressing the case where data from the source domain is abundant, labelled data from the target domain is limited or non-existent, and a small amount of paired source-target data is available.…
Machine learning techniques in neutrino physics have traditionally relied on simulated data, which provides access to ground-truth labels. However, the accuracy of these simulations and the discrepancies between simulated and real data…
In many manufacturing settings, annotating data for machine learning and computer vision is costly, but synthetic data can be generated at significantly lower cost. Substituting the real-world data with synthetic data is therefore appealing…
LiDAR object detection algorithms based on neural networks for autonomous driving require large amounts of data for training, validation, and testing. As real-world data collection and labeling are time-consuming and expensive,…
Currently, under supervised learning, a model pretrained by a large-scale nature scene dataset and then fine-tuned on a few specific task labeling data is the paradigm that has dominated the knowledge transfer learning. It has reached the…
Semi-Supervised Learning (SSL) is a framework that utilizes both labeled and unlabeled data to enhance model performance. Conventional SSL methods operate under the assumption that labeled and unlabeled data share the same label space.…
Popular zero-shot models suffer due to artifacts inherited from pretraining. One particularly detrimental issue, caused by unbalanced web-scale pretraining data, is mismatched label distribution. Existing approaches that seek to repair the…
We discuss how to achieve mapping from large sets of imperfect simulations and observational data with unsupervised domain adaptation. Under the hypothesis that simulated and observed data distributions share a common underlying…
Domain adaptation helps generalizing object detection models to target domain data with distribution shift. It is often achieved by adapting with access to the whole target domain data. In a more realistic scenario, target distribution is…
Few-shot image classification remains challenging due to the scarcity of labeled training examples. Augmenting them with synthetic data has emerged as a promising way to alleviate this issue, but models trained on synthetic samples often…
Generative modeling of time series is a central challenge in time series analysis, particularly under data-scarce conditions. Despite recent advances in generative modeling, a comprehensive understanding of how state-of-the-art generative…
The lack of large annotated datasets in medical imaging is an intrinsic burden for supervised Deep Learning (DL) segmentation models. Few-shot learning approaches are cost-effective solutions to transfer pre-trained models using only…
We consider the novel problem of unsupervised domain adaptation of source models, without access to the source data for semantic segmentation. Unsupervised domain adaptation aims to adapt a model learned on the labeled source data, to a new…
Zero-Shot Learning (ZSL) is a classification task where we do not have even a single training labeled example from a set of unseen classes. Instead, we only have prior information (or description) about seen and unseen classes, often in the…
Time-series representation learning can extract representations from data with temporal dynamics and sparse labels. When labeled data are sparse but unlabeled data are abundant, contrastive learning, i.e., a framework to learn a latent…
Conventional approaches to text classification typically assume the existence of a fixed set of predefined labels to which a given text can be classified. However, in real-world applications, there exists an infinite label space for…
Deep neural networks (DNNs) have achieved state-of-the-art results on time series classification (TSC) tasks. In this work, we focus on leveraging DNNs in the often-encountered practical scenario where access to labeled training data is…