document

Automated Semantic Segmentation of Aerial Imagery using Synthetic Data

Caceres Tocora, Camilo (author)

Semantic segmentation of aerial images is the ability to assign labels to all pixels of an image. It proves to be essential for various applications such as urban planning, agriculture and real-estate analysis. Deep Learning techniques have shown satisfactory results in performing semantic segmentation tasks. Training a deep learning model is an...

master thesis 2022

document

Unpaired day-night domain adaptation using CycleGANs combined with CIConv

Streefkerk, Thomas (author)

CycleGANs [1] and CIConv [2] are both relatively new approaches to their respective applications. For CycleGANs this application is unpaired image-to-image domain adaptation and for CIConv this application is making images more<br/>robust to illumination changes. We investigate whether CycleGANs in combination with CIConv can be used to improve...

bachelor thesis 2022

document

A trainable Gaussian color model for determining the color invariant

Gioia, Gianpaolo (author)

The possibility to improve an existing method by making (part of) it learnable is explored in this research. The work that this research extends added prior knowledge to a Convolutional Neural Network (CNN) to improve its performance when dealing with an illumination shift. The method used for the preprocessing, is the color invariant. The...

bachelor thesis 2022

document

Color Invariant Convolution for semantic segmentation

Ju, Nicky (author)

Color Invariant Convolution (CIConv) is a learnable Convolutional Neural Network (CNN) layer that reduces the distribution shift between the source and target set in the CNN under an illumination-based domain shift. We explore the semantic segmentation performance for daynight domain adaptation when using CIConv. We will test this on two...

bachelor thesis 2022

document

Unsupervised Domain Adaptation for Disguised-gait-based Person Identification on Micro-Doppler Signatures

Yang, Yang (author), Yang, Xiaoyi (author), Sakamoto, Takuya (author), Fioranelli, F. (author), Li, Beichen (author), Lang, Yue (author)

In recent years, gait-based person identification has gained significant interest for a variety of applications, including security systems and public security forensics. Meanwhile, this task is faced with the challenge of disguised gaits. When a human subject changes what he or she is wearing or carrying, it becomes challenging to reliably...

journal article 2022

document

On-ground validation of a CNN-based monocular pose estimation system for uncooperative spacecraft: Bridging domain shift in rendezvous scenarios

Pasqualetto Cassinis, L. (author), Menicucci, A. (author), Gill, E.K.A. (author), Ahrns, Ingo (author), Sanchez-Gestido, Manuel (author)

The estimation of the relative pose of an inactive spacecraft by an active servicer spacecraft is a critical task for close-proximity operations, such as In-Orbit Servicing and Active Debris Removal. Among all the challenges, the lack of available space images of the inactive satellite makes the on-ground validation of current monocular...

journal article 2022

document

Dynamic transfer partial least squares for domain adaptive regression

Zhao, Zhijun (author), Yan, Gaowei (author), Ren, Mifeng (author), Cheng, Lan (author), Zhu, Zhujun (author), Pang, Y. (author)

The traditional soft sensor models are based on the independent and identical distribution assumption, which are difficult to adapt to changes in data distribution under multiple operating conditions, resulting in model performance deterioration. The domain adaptive transfer learning methods learn knowledge in different domains by means of...

journal article 2022

document

Estimating the transferability of state-of-the-art models in predicting moral values

Dondera, Alin (author)

Moral values play a crucial role in our decision-making process by defining what is right and wrong. With the emergence of political activism and moral discourse on social media, and the latest developments in Natural Language Processing, we are looking at an opportunity to analyze moral values to observe trends as they form. Recent studies have...

bachelor thesis 2021

document

Domain Adaptation for Rare Classes Augmented with Synthetic Samples

Das, Tuhin (author)

To alleviate lower classification performance on rare classes in imbalanced datasets, a possible solution is to augment the underrepresented classes with synthetic samples. Domain adaptation can be incorporated in a classifier to decrease the domain discrepancy between real and synthetic samples. While domain adaptation is...

bachelor thesis 2021

document

Exploring the Potential of Performance Bounds in Multi-Source Domain Adaptation

Bons, Wouther (author)

Currently, trained machine learning models are readily available, but their training data might not be (for example due to privacy reasons). This thesis investigates how pre-trained models can be combined for performance on all their source domains, without access to data. This problem is formulated as a Multiple-Source Domain Adaptation (MSA)...

master thesis 2021

document

Domain adaptation for target classification using micro-Doppler spectra in radar networks

Svenningsson, P.O. (author), Fioranelli, F. (author), Yarovoy, Alexander (author)

In this paper, the classification of human activity from micro-Doppler spectrograms measured by a radar network is considered. To cope with differences between the training and test datasets due to changes in the set of participants, signal-to-noise ratio and polarimetry, domain adaptation is proposed. To realize this, linear mapping between the...

conference paper 2021

document

Robust domain-adaptive discriminant analysis

Kouw, W.M. (author), Loog, M. (author)

Consider a domain-adaptive supervised learning setting, where a classifier learns from labeled data in a source domain and unlabeled data in a target domain to predict the corresponding target labels. If the classifier’s assumption on the relationship between domains (e.g. covariate shift, common subspace, etc.) is valid, then it will usually...

journal article 2021

document

Acoustic Perception in Intelligent Vehicles using a single microphone system

Mattar, Avinash (author)

Passive acoustic sensing utilizes the ability of sound to travel beyond the line-of-sight to understand the surroundings. This provides an advantage over the currently used sensors in Intelligent Vehicles that can sense obstacles within their line-of-sight only. Recently, a localization based approach has been implemented to take advantage of...

master thesis 2020

document

Weight Swapping: A new method for Supervised Domain Adaptation in Computer Vision using Discrete Optimization

Datta, Leonid (author)

Training Convolutional Neural Network (CNN) models is difficult when there is a lack of labeled training data and no unlabeled data is available. A popular method for this is domain adaptation where the weights of a pre-trained CNN model are transferred to the problem setup. The model is pre-trained on the same task but in a different domain...

master thesis 2020

document

Domain Adaptation in Acoustic Rainfall Sensors

Naseri Jahfari, Arman (author)

Rainfall is increasing in frequency and intensity due to climate change. Hydrological models exist that can report bottlenecks in urban infrastructures. However, these require accurate rainfall estimations with high temporal and spatial resolution. The fulfillment of these requirements is challenged due to high costs. This can be solved with...

master thesis 2019

document

Detecting speech from body movements: A look into the nature of speech based on neural networks and multi-source domain adaptation

Ni, Xianhao (author)

Our research focuses on speech detection from body movements using wearable accelerometer data collected in an in-the-wild mingling event. We aim to explore the nature of the connection between speech and body movements. More specifically, we stress on the person-specificity of speech. Many studies have shown that speech always comes along with...

master thesis 2019

document

Attention-Aware Age-Agnostic Visual Place Recognition

Li, Jiahui (author)

A cross-domain visual place recognition (VPR) task is proposed in this work, i.e., matching images of the same architectures depicted in different domains. VPR is commonly treated as an image retrieval task, where a query image from an unknown location is matched with relevant instances from geo-tagged gallery database. Different from...

master thesis 2019

document

Addressing Illumination-Based Domain Shifts in Deep Learning: A Physics-Based Approach

Lengyel, Attila (author)

This work investigates how prior knowledge from physics-based reflection models can be used to improve the performance of semantic segmentation models under an illumination-based domain shift. We implement various color invariants as a preprocessing step and find that CNNs trained on these color invariants get stuck in worse local minima...

master thesis 2019

document

Cross Domain Image Matching in Presence of Outliers

Liu, X. (author), Khademi, S. (author), van Gemert, J.C. (author)

Cross domain image matching between image collections from different source and target domains is challenging in times of deep learning due to i) limited variation of image conditions in a training set, ii) lack of paired-image labels during training, iii) the existing of outliers that makes image matching domains not fully overlap. To this end,...

conference paper 2019

document

Soft sensor for ball mill load based on multi-view domain adaptation learning

Guo, Xuqi (author), Yan, F. (author), Pang, Y. (author), Yan, Gaowei (author)

In the operation process of wet ball mill, there are often multi-modal and multi-condition problems. In this paper, a multi-view based domain adaptive extreme learning machine (MVDAELM) was used to measure the mill load. Firstly, the correlation relationship between the load parameters and the two views (vibration and acoustic signals of the...

conference paper 2019