Related papers: Look, Radiate, and Learn: Self-Supervised Localisa…
In this paper we present three different applications, based on deep learning methodologies, that we are developing to support the scientific analysis conducted within the ASKAP-EMU and MeerKAT radio surveys. One employs instance…
Searching for fleeting radio transients like fast radio bursts (FRBs) with wide-field radio telescopes has become a common challenge in data-intensive science. Conventional algorithms normally cost enormous time to seek candidates by…
Generalising deep networks to novel domains without manual labels is challenging to deep learning. This problem is intrinsically difficult due to unpredictable changing nature of imagery data distributions in novel domains. Pre-learned…
Recently, deep neural networks have achieved remarkable performance on the task of object detection and recognition. The reason for this success is mainly grounded in the availability of large scale, fully annotated datasets, but the…
Collecting large annotated datasets in Remote Sensing is often expensive and thus can become a major obstacle for training advanced machine learning models. Common techniques of addressing this issue, based on the underlying idea of…
In this paper, we introduce a novel geometry-aware self-training framework for room layout estimation models on unseen scenes with unlabeled data. Our approach utilizes a ray-casting formulation to aggregate multiple estimates from…
Despite the impressive improvements achieved by unsupervised deep neural networks in computer vision and NLP tasks, such improvements have not yet been observed in ranking for information retrieval. The reason may be the complexity of the…
We learn, in an unsupervised way, an embedding from sequences of radar images that is suitable for solving the place recognition problem with complex radar data. Our method is based on invariant instance feature learning but is tailored for…
Network capacity expansion is a critical challenge for telecom operators, requiring strategic placement of new cell sites to ensure optimal coverage and performance. Traditional approaches, such as manual drive tests and static…
Deep learning has achieved unprecedented success in various object detection tasks with huge amounts of labeled data. However, obtaining large-scale annotations for medical images is extremely challenging due to the high demand of labour…
We investigate and improve self-supervision as a drop-in replacement for ImageNet pretraining, focusing on automatic colorization as the proxy task. Self-supervised training has been shown to be more promising for utilizing unlabeled data…
Distinguishing visually similar objects by their motion remains a critical challenge in computer vision. Although supervised trackers show promise, contemporary self-supervised trackers struggle when visual cues become ambiguous, limiting…
Accurate localization in diverse environments is a fundamental challenge in computer vision and robotics. The task involves determining a sensor's precise position and orientation, typically a camera, within a given space. Traditional…
We consider the question: what can be learnt by looking at and listening to a large number of unlabelled videos? There is a valuable, but so far untapped, source of information contained in the video itself -- the correspondence between the…
A novel framework to enhance the angular resolution of automotive radars is proposed. An approach to enlarge the antenna aperture using artificial neural networks is developed using a self-supervised learning scheme. Data from a high…
Stereo matching in remote sensing has recently garnered increased attention, primarily focusing on supervised learning. However, datasets with ground truth generated by expensive airbone Lidar exhibit limited quantity and diversity,…
Adaptability is central to autonomy. Intuitively, for high-dimensional learning problems such as navigating based on vision, internal models with higher complexity allow to accurately encode the information available. However, most learning…
Accurate analysis of microscopy images is hindered by the presence of noise. This noise is usually signal-dependent and often additionally correlated along rows or columns of pixels. Current self- and unsupervised denoisers can address…
For applications in e-commerce, warehouses, healthcare, and home service, robots are often required to search through heaps of objects to grasp a specific target object. For mechanical search, we introduce X-Ray, an algorithm based on…
Recent developments in the remote sensing systems and image processing made it possible to propose a new method of the object classification and detection of the specific changes in the series of satellite Earth images (so called targeted…