Related papers: Representative-Discriminative Learning for Open-se…

The application of deep neural networks to remote sensing imagery is often constrained by the lack of ground-truth annotations. Adressing this issue requires models that generalize efficiently from limited amounts of labeled data, allowing…

Fueled by deep learning, computer-aided diagnosis achieves huge advances. However, out of controlled lab environments, algorithms could face multiple challenges. Open set recognition (OSR), as an important one, states that categories unseen…

Deep convolutional models often produce inadequate predictions for inputs foreign to the training distribution. Consequently, the problem of detecting outlier images has recently been receiving a lot of attention. Unlike most previous work,…

With the human pursuit of knowledge, open-set object detection (OSOD) has been designed to identify unknown objects in a dynamic world. However, an issue with the current setting is that all the predicted unknown objects share the same…

Remote sensing data has been widely used for various Earth Observation (EO) missions such as land use and cover classification, weather forecasting, agricultural management, and environmental monitoring. Most existing remote sensing…

Clever sampling methods can be used to improve the handling of big data and increase its usefulness. The subject of this study is remote sensing, specifically airborne laser scanning point clouds representing different classes of ground…

The use of satellite imagery combined with deep learning to support automatic landslide detection is becoming increasingly widespread. However, selecting an appropriate deep learning architecture to optimize performance while avoiding…

The problem of detecting a novel class at run time is known as Open Set Detection & is important for various real-world applications like medical application, autonomous driving, etc. Open Set Detection within context of deep learning…

Open Set Domain Adaptation (OSDA) bridges the domain gap between a labeled source domain and an unlabeled target domain, while also rejecting target classes that are not present in the source. To avoid negative transfer, OSDA can be tackled…

Open-World Recognition (OWR) is an emerging field that makes a machine learning model competent in rejecting the unknowns, managing them, and incrementally adding novel samples to the base knowledge. However, this broad objective is not…

This paper proposes a few-shot method based on Faster R-CNN and representation learning for object detection in aerial images. The two classification branches of Faster R-CNN are replaced by prototypical networks for online adaptation to…

The success of supervised classification of remotely sensed images acquired over large geographical areas or at short time intervals strongly depends on the representativity of the samples used to train the classification algorithm and to…

Deep learners tend to perform well when trained under the closed set assumption but struggle when deployed under open set conditions. This motivates the field of Open Set Recognition in which we seek to give deep learners the ability to…

A typical assumption in state-of-the-art self-localization models is that an annotated training dataset is available for the target workspace. However, this is not necessarily true when a robot travels around the general open world. This…

We describe an approach to learning rich representations for images, that enables simple and effective predictors in a range of vision tasks involving spatially structured maps. Our key idea is to map small image elements to feature…

In recent years, the remarkable success of deep neural networks (DNNs) in computer vision is largely due to large-scale, high-quality labeled datasets. Training directly on real-world datasets with label noise may result in overfitting. The…

Deep learning models are essential for scene classification, change detection, land cover segmentation, and other remote sensing image understanding tasks. Most backbones of existing remote sensing deep learning models are typically…

In this work, we introduce the concept of Active Representation Learning, a novel class of problems that intertwines exploration and representation learning within partially observable environments. We extend ideas from Active Simultaneous…

Current hyperspectral image classification assumes that a predefined classification system is closed and complete, and there are no unknown or novel classes in the unseen data. However, this assumption may be too strict for the real world.…

The primary assumption of conventional supervised learning or classification is that the test samples are drawn from the same distribution as the training samples, which is called closed set learning or classification. In many practical…