Related papers: MaskIt: Masking for efficient utilization of incom…

A fundamental challenge of over-parameterized deep learning models is learning meaningful data representations that yield good performance on a downstream task without over-fitting spurious input features. This work proposes MaskTune, a…

Supervised deep learning models require significant amount of labeled data to achieve an acceptable performance on a specific task. However, when tested on unseen data, the models may not perform well. Therefore, the models need to be…

Automatic road extraction from satellite imagery using deep learning is a viable alternative to traditional manual mapping. Therefore it has received considerable attention recently. However, most of the existing methods are supervised and…

Structure inference is an important task for network data processing and analysis in data science. In recent years, quite a few approaches have been developed to learn the graph structure underlying a set of observations captured in a data…

Mapping standing dead trees is critical for assessing forest health, monitoring biodiversity, and mitigating wildfire risks, for which aerial imagery has proven useful. However, dense canopy structures, spectral overlaps between living and…

Aerial image segmentation is the basis for applications such as automatically creating maps or tracking deforestation. In true orthophotos, which are often used in these applications, many objects and regions can be approximated well by…

Deep networks have produced significant gains for various visual recognition problems, leading to high impact academic and commercial applications. Recent work in deep networks highlighted that it is easy to generate images that humans…

Although deep networks have recently emerged as the model of choice for many computer vision problems, in order to yield good results they often require time-consuming architecture search. To combat the complexity of design choices, prior…

High-performance visual recognition systems generally require a large collection of labeled images to train. The expensive data curation can be an obstacle for improving recognition performance. Sharing more data allows training for better…

Commercial companies that collect user data on a large scale have been the main beneficiaries of this trend since the success of deep learning techniques is directly proportional to the amount of data available for training. Massive data…

Deep learning has proven itself as a successful set of models for learning useful semantic representations of data. These, however, are mostly implicitly learned as part of a classification task. In this paper we propose the triplet network…

Deep learning applications in shaping ad hoc planning proposals are limited by the difficulty in integrating professional knowledge about cities with artificial intelligence. We propose a novel, complementary use of deep neural networks and…

Road networks are a type of spatial network, where edges may be associated with qualitative information such as road type and speed limit. Unfortunately, such information is often incomplete; for instance, OpenStreetMap only has speed…

Many machine learning algorithms are trained and evaluated by splitting data from a single source into training and test sets. While such focus on in-distribution learning scenarios has led to interesting advancement, it has not been able…

Airborne hyperspectral images can be used to map the land cover in large urban areas, thanks to their very high spatial and spectral resolutions on a wide spectral domain. While the spectral dimension of hyperspectral images is highly…

We introduce a novel self-supervised learning framework that automatically learns representations from input computer-aided design (CAD) models for downstream tasks, including part classification, modeling segmentation, and machining…

Data generated by edge devices has the potential to train intelligent autonomous systems across various domains. Despite the emergence of diverse machine learning approaches addressing privacy concerns and utilizing distributed data,…

Beyond the immediate biophysical benefits, urban trees play a foundational role in environmental sustainability and disaster mitigation. Precise mapping of urban trees is essential for environmental monitoring, post-disaster assessment, and…

Deep learning models have been used extensively to solve real-world problems in recent years. The performance of such models relies heavily on large amounts of labeled data for training. While the advances of data collection technology have…

2D top-down maps are commonly used for the navigation and exploration of mobile robots through unknown areas. Typically, the robot builds the navigation maps incrementally from local observations using onboard sensors. Recent works have…