Related papers: Auto-Test: Learning Semantic-Domain Constraints fo…

Training models dedicated to semantic segmentation requires a large amount of pixel-wise annotated data. Due to their costly nature, these annotations might not be available for the task at hand. To alleviate this problem, unsupervised…

Semantic segmentation models only perform well on the domain they are trained on and datasets for training are scarce and often have a small label-spaces, because the pixel level annotations required are expensive to make. Thus training…

Self-supervised features are the cornerstone of modern machine learning systems. They are typically pre-trained on data collections whose construction and curation typically require extensive human effort. This manual process has some…

Although deep neural networks have achieved remarkable results for the task of semantic segmentation, they usually fail to generalize towards new domains, especially when performing synthetic-to-real adaptation. Such domain shift is…

Using deep learning, we now have the ability to create exceptionally good semantic segmentation systems; however, collecting the prerequisite pixel-wise annotations for training images remains expensive and time-consuming. Therefore, it…

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…

Deep convolutional neural networks for semantic segmentation achieve outstanding accuracy, however they also have a couple of major drawbacks: first, they do not generalize well to distributions slightly different from the one of the…

Unsupervised domain adaptation aims to address the problem of classifying unlabeled samples from the target domain whilst labeled samples are only available from the source domain and the data distributions are different in these two…

Considerable research attention has been paid to table detection by developing not only rule-based approaches reliant on hand-crafted heuristics but also deep learning approaches. Although recent studies successfully perform table detection…

Deep learning has made revolutionary advances to diverse applications in the presence of large-scale labeled datasets. However, it is prohibitively time-costly and labor-expensive to collect sufficient labeled data in most realistic…

Data quality problems are a large threat in data science. In this paper, we propose a data-cleaning autoencoder capable of near-automatic data quality improvement. It learns the structure and dependencies in the data and uses it as evidence…

Domain adaptive semantic segmentation aims to learn a model with the supervision of source domain data, and produce satisfactory dense predictions on unlabeled target domain. One popular solution to this challenging task is self-training,…

The rise of deep learning in natural language processing has fostered the creation of text to structured query language models composed of an encoder and a decoder. Researchers have experimented with various intermediate processing like…

Machine learning systems must adapt to data distributions that evolve over time, in applications ranging from sensor networks and self-driving car perception modules to brain-machine interfaces. We consider gradual domain adaptation, where…

Accurate product information is critical for e-commerce stores to allow customers to browse, filter, and search for products. Product data quality is affected by missing or incorrect information resulting in poor customer experience. While…

We propose a novel setting for learning, where the input domain is the image of a map defined on the product of two sets, one of which completely determines the labels. We derive a new risk bound for this setting that decomposes into a bias…

Self-supervised learning on tabular data seeks to apply advances from natural language and image domains to the diverse domain of tables. However, current techniques often struggle with integrating multi-domain data and require data…

This paper presents a novel method for discovering systematic errors in segmentation models. For instance, a systematic error in the segmentation model can be a sufficiently large number of misclassifications from the model as a parking…

Domain adaptation (DA) mitigates the domain shift problem when transferring knowledge from one annotated domain to another similar but different unlabeled domain. However, existing models often utilize one of the ImageNet models as the…

Although deep learning has demonstrated astonishing performance in many applications, there are still concerns about its dependability. One desirable property of deep learning applications with societal impact is fairness (i.e.,…