Global ETD Search

1	Alternative Solution to Catastrophical Forgetting on FewShot Instance Segmentation Álvarez Fernández Del Vallado, Juan January 2021 (has links) Video instance segmentation is a rapidly-growing research area within the computer vision field. Models for segmentation require data already annotated, which can be a daunting task when starting from scratch. Although there are some publicly available datasets for image instance segmentation, they are limited to the application they target. This work proposes a new approach to training an instance segmentation model using transfer learning, notably reducing the need for annotated data. Transferring knowledge from domain A to domain B can result in catastrophical forgetting, leading to an algorithm unable to properly generalize and remember the previous knowledge acquired at the initial domain. This problem is studied and a solution is proposed based on data transformations applied precisely at the process of transferring knowledge to the target domain following the empirical research method and using publicly available video instance segmentation datasets as resources for the experiments. Conclusions show there is a relationship between the data transformations and ability to generalize both domains. / Segmentering av videointervjuer är ett snabbt växande forskningsområde inom datorseende. Modeller för segmentering kräver data som redan är annoterade, vilket kan vara en krävande uppgift när man börjar från början. Även om det finns några offentligt tillgängliga datamängder för bildinstanssegmentering är de begränsade till den tillämpning de är inriktade på. I detta arbete föreslås en ny metod för att träna en modell för instanssegmentering med hjälp av överföringsinlärning, vilket framför allt minskar behovet av annoterade data. Överföring av kunskap från domän A till domän B kan resultera i katastrofal glömska, vilket leder till att en algoritm inte kan generalisera och komma ihåg den tidigare kunskap som förvärvats i den ursprungliga domänen. Detta problem studeras och en lösning föreslås som bygger på datatransformationer som tillämpas just vid överföringen av kunskap till måldomänen enligt den empiriska forskningsmetoden och med hjälp av offentligt tillgängliga datamängder för segmentering av videointervjuer som resurser för experimenten. Slutsatserna visar att det finns ett samband mellan datatransformationer och förmågan att generalisera båda områdena. Machine learning big data transfer learning computer vision instance segmentation Maskininlärning stora datamängder datorseende instanssegmentering objektdetektering detectron2 Computer and Information Sciences Data- och informationsvetenskap
2	Using Mask R-CNN for Instance Segmentation of Eyeglass Lenses / Användning av Mask R-CNN för instanssegmentering av glasögonlinser Norrman, Marcus, Shihab, Saad January 2021 (has links) This thesis investigates the performance of Mask R-CNN when utilizing transfer learning on a small dataset. The aim was to instance segment eyeglass lenses as accurately as possible from self-portrait images. Five different models were trained, where the key difference was the types of eyeglasses the models were trained on. The eyeglasses were grouped into three types, fully rimmed, semi-rimless, and rimless glasses. 1550 images were used for training, validation, and testing. The model's performances were evaluated using TensorBoard training data and mean Intersection over Union scores (mIoU). No major differences in performance were found in four of the models, which grouped all three types of glasses into one class. Their mIoU scores range from 0.913 to 0.94 whereas the model with one class for each group of glasses, performed worse, with a mIoU of 0.85. The thesis revealed that one can achieve great instance segmentation results using a limited dataset when taking advantage of transfer learning. / Denna uppsats undersöker prestandan för Mask R-CNN vid användning av överföringsinlärning på en liten datamängd. Syftet med arbetet var att segmentera glasögonlinser så exakt som möjligt från självporträttbilder. Fem olika modeller tränades, där den viktigaste skillnaden var de typer av glasögon som modellerna tränades på. Glasögonen delades in i 3 typer, helbåge, halvbåge och båglösa. Totalt samlades 1550 träningsbilder in, dessa annoterades och användes för att träna modellerna. Modellens prestanda utvärderades med TensorBoard träningsdata samt genomsnittlig Intersection over Union (IoU). Inga större skillnader i prestanda hittades mellan modellerna som endast tränades på en klass av glasögon. Deras genomsnittliga IoU varierar mellan 0,913 och 0,94. Modellen där varje glasögonkategori representerades som en unik klass, presterade sämre med en genomsnittlig IoU på 0,85. Resultatet av uppsatsen påvisar att goda instanssegmenteringsresultat går att uppnå med hjälp av en begränsad datamängd om överföringsinlärning används. Machine Learning Computer Vision Instance Segmentation Mask R-CNN CNN Convolutional Neural Networks Transfer Learning Maskininlärning Datorseende Instanssegmentering Mask R-CNN CNN Konvolutionella neurala nätverk Överföringsinlärning Mathematics Matematik
3	Instance Segmentation for Printed Circuit Board (PCB) Component Analysis : Exploring CNNs and Transformers for Component Detection on Printed Circuit Boards Möller, Oliver January 2023 (has links) In the intricate domain of Printed Circuit Boards (PCBs), object detection poses unique challenges, particularly given the broad size spectrum of components, ranging from a mere 2 pixels to several thousand pixels within a single high-resolution image, often averaging 4000x3000 pixels. Such resolutions are atypical in the realm of deep learning for computer vision, making the task even more demanding. Further complexities arise from the significant intra-class variability and minimal inter-class differences for certain component classes. In this master thesis, we rigorously evaluated the performance of a CNN-based object detection framework (FCOS) and a transformer model (DETR) for the task. Additionally, by integrating the novel foundational model from Meta, named ”Segment Anything,” we advanced the pipeline to include instance segmentation. The resultant model is proficient in detecting and segmenting component instances on PCB images, achieving an F1 score of 81% and 82% for the primary component classes of resistors and capacitors, respectively. Overall, when aggregated over 18 component classes, the model attains a commendable F1 score of 74%. This study not only underscores the potential of advanced deep learning techniques in PCB analysis but also paves the way for future endeavors in this interdisciplinary convergence of electronics and computer vision / I det komplicerade området med kretskort (PCB) innebär objektdetektering unika utmaningar, särskilt med tanke på det breda storleksspektrumet av komponenter, från bara 2 pixlar till flera tusen pixlar i en enda högupplöst bild, ofta i genomsnitt 4000x3000 pixlar. Sådana upplösningar är atypiska när det gäller djupinlärning för datorseende, vilket gör uppgiften ännu mer krävande. Ytterligare komplexitet uppstår från den betydande variationen inom klassen och minimala skillnader mellan klasserna för vissa komponentklasser. I denna masteruppsats utvärderade vi noggrant prestandan hos ett CNNbaserat ramverk för objektdetektering (FCOS) och en transformatormodell (DETR) för uppgiften. Genom att integrera den nya grundmodellen från Meta, med namnet ”Segment Anything”, utvecklade vi dessutom pipelinen för att inkludera instanssegmentering. Den resulterande modellen är skicklig på att upptäcka och segmentera komponentinstanser på PCB-bilder och uppnår en F1-poäng på 81% och 82% för de primära komponentklasserna resistorer respektive kondensatorer. När modellen aggregeras över 18 komponentklasser uppnår den en F1-poäng på 74%. Denna studie understryker inte bara potentialen hos avancerade djupinlärningstekniker vid PCB-analys utan banar också väg för framtida insatser inom denna tvärvetenskapliga konvergens av elektronik och datorseende. Deep Learning Computer Vision Image Processing Object Detection Instance Segmentation Printed Circuit Board (PCB) Djupinlärning Datorseende Bildbehandling Objektdetektering Instanssegmentering Tryckt kretskort Computer and Information Sciences Data- och informationsvetenskap
4	AI-based Quality Inspection forShort-Series Production : Using synthetic dataset to perform instance segmentation forquality inspection / AI-baserad kvalitetsinspektion för kortserieproduktion : Användning av syntetiska dataset för att utföra instans segmentering förkvalitetsinspektion Russom, Simon Tsehaie January 2022 (has links) Quality inspection is an essential part of almost any industrial production line. However, designing customized solutions for defect detection for every product can be costlyfor the production line. This is especially the case for short-series production, where theproduction time is limited. That is because collecting and manually annotating the training data takes time. Therefore, a possible method for defect detection using only synthetictraining data focused on geometrical defects is proposed in this thesis work. The methodis partially inspired by previous related work. The proposed method makes use of aninstance segmentation model and pose-estimator. However, this thesis work focuses onthe instance segmentation part while using a pre-trained pose-estimator for demonstrationpurposes. The synthetic data was automatically generated using different data augmentation techniques from a 3D model of a given object. Moreover, Mask R-CNN was primarilyused as the instance segmentation model and was compared with a rival model, HTC. Thetrials show promising results in developing a trainable general-purpose defect detectionpipeline using only synthetic data Synthetic Training Dataset Geometrical Defect Detection Instance Segmentation Data Augmentation Techniques Mask R-CNN Transformers Syntetisk Träningsdataset Detektion av Geometriska Defekter Instanssegmentering Tekniker för Dataaugmentering Mask R-CNN Transformers
5	Instance Segmentation of Multiclass Litter and Imbalanced Dataset Handling : A Deep Learning Model Comparison / Instanssegmentering av kategoriserat skräp samt hantering av obalanserat dataset Sievert, Rolf January 2021 (has links) Instance segmentation has a great potential for improving the current state of littering by autonomously detecting and segmenting different categories of litter. With this information, litter could, for example, be geotagged to aid litter pickers or to give precise locational information to unmanned vehicles for autonomous litter collection. Land-based litter instance segmentation is a relatively unexplored field, and this study aims to give a comparison of the instance segmentation models Mask R-CNN and DetectoRS using the multiclass litter dataset called Trash Annotations in Context (TACO) in conjunction with the Common Objects in Context precision and recall scores. TACO is an imbalanced dataset, and therefore imbalanced data-handling is addressed, exercising a second-order relation iterative stratified split, and additionally oversampling when training Mask R-CNN. Mask R-CNN without oversampling resulted in a segmentation of 0.127 mAP, and with oversampling 0.163 mAP. DetectoRS achieved 0.167 segmentation mAP, and improves the segmentation mAP of small objects most noticeably, with a factor of at least 2, which is important within the litter domain since small objects such as cigarettes are overrepresented. In contrast, oversampling with Mask R-CNN does not seem to improve the general precision of small and medium objects, but only improves the detection of large objects. It is concluded that DetectoRS improves results compared to Mask R-CNN, as well does oversampling. However, using a dataset that cannot have an all-class representation for train, validation, and test splits, together with an iterative stratification that does not guarantee all-class representations, makes it hard for future works to do exact comparisons to this study. Results are therefore approximate considering using all categories since 12 categories are missing from the test set, where 4 of those were impossible to split into train, validation, and test set. Further image collection and annotation to mitigate the imbalance would most noticeably improve results since results depend on class-averaged values. Doing oversampling with DetectoRS would also help improve results. There is also the option to combine the two datasets TACO and MJU-Waste to enforce training of more categories. Machine learning Multiclass Deep learning Instance segmentation Object segmentation Iterative stratification Mask R-CNN DetectoRS Imbalanced dataset Classification Detection Segmentation Litter Trash TACO COCO MMDetection Multinomial Cybercom AI Artificial intelligence Land-based litter Computer vision Maskininlärning Djupinlärning Instanssegmentering Objektsegmentering Mask R-CNN DetectoRS Obalanserat dataset Klassificering Detektion Segmentering Skräp TACO COCO MMDetection Multinomial Cybercom AI Artificiell intelligens Datorseende

1

Page generated in 0.1149 seconds