Related papers: Lifelong Change Detection: Continuous Domain Adapt…

Although deep networks have significantly increased the performance of visual recognition methods, it is still challenging to achieve the robustness across visual domains that is necessary for real-world applications. To tackle this issue,…

We introduce a novel approach for scalable domain adaptation in cloud robotics scenarios where robots rely on third-party AI inference services powered by large pre-trained deep neural networks. Our method is based on a downstream…

Domain adaptation is especially important for robotics applications, where target domain training data is usually scarce and annotations are costly to obtain. We present a method for self-supervised domain adaptation for the scenario where…

Ground robots require the crucial capability of traversing unstructured and unprepared terrains and avoiding obstacles to complete tasks in real-world robotics applications such as disaster response. When a robot operates in off-road field…

State-of-the-art object detection methods applied to satellite and drone imagery largely fail to identify small and dense objects. One reason is the high variability of content in the overhead imagery due to the terrestrial region captured…

The ability to evolve is fundamental for any valuable autonomous agent whose knowledge cannot remain limited to that injected by the manufacturer. Consider for example a home assistant robot: it should be able to incrementally learn new…

Uniform and variable environments still remain a challenge for stable visual localization and mapping in mobile robot navigation. One of the possible approaches suitable for such environments is appearance-based teach-and-repeat navigation,…

Reliable perception and efficient adaptation to novel conditions are priority skills for humanoids that function in dynamic environments. The vast advancements in latest computer vision research, brought by deep learning methods, are…

Multiple object tracking (MOT) is a fundamental component of perception systems for autonomous driving, and its robustness to unseen conditions is a requirement to avoid life-critical failures. Despite the urge of safety in driving systems,…

Typically a classifier trained on a given dataset (source domain) does not performs well if it is tested on data acquired in a different setting (target domain). This is the problem that domain adaptation (DA) tries to overcome and, while…

Modern models that perform system-critical tasks such as segmentation and localization exhibit good performance and robustness under ideal conditions (i.e. daytime, overcast) but performance degrades quickly and often catastrophically when…

Supervised learning tends to produce more accurate classifiers than unsupervised learning in general. This implies that training data is preferred with annotations. When addressing visual perception challenges, such as localizing certain…

Deep domain adaption has emerged as a new learning technique to address the lack of massive amounts of labeled data. Compared to conventional methods, which learn shared feature subspaces or reuse important source instances with shallow…

We present a novel approach to perform the unsupervised domain adaptation for object detection through forward-backward cyclic (FBC) training. Recent adversarial training based domain adaptation methods have shown their effectiveness on…

Object detection from Unmanned Aerial Vehicles (UAVs) is of great importance in many aerial vision-based applications. Despite the great success of generic object detection methods, a significant performance drop is observed when applied to…

In this paper, we propose subspace alignment based domain adaptation of the state of the art RCNN based object detector. The aim is to be able to achieve high quality object detection in novel, real world target scenarios without requiring…

Domain adaptation is a crucial and increasingly important task in remote sensing, aiming to transfer knowledge from a source domain a differently distributed target domain. It has broad applications across various real-world applications,…

In precision agriculture, vision models often struggle with new, unseen fields where crops and weeds have been influenced by external factors, resulting in compositions and appearances that differ from the learned distribution. This paper…

Learning visuomotor control policies in robotic systems is a fundamental problem when aiming for long-term behavioral autonomy. Recent supervised-learning-based vision and motion perception systems, however, are often separately built with…

Change detection (CD) is to decouple object changes (i.e., object missing or appearing) from background changes (i.e., environment variations) like light and season variations in two images captured in the same scene over a long time span,…