Essays about: "ImageNet"
Showing result 6 - 10 of 48 essays containing the word ImageNet.
-
6. Few-Shot Learning for Quality Inspection
University essay from Högskolan i Halmstad/Akademin för informationsteknologiAbstract : The goal of this project is to find a suitable Few-Shot Learning (FSL) model that can be used in a fault detection system for use in an industrial setting. A dataset of Printed Circuit Board (PCB) images has been created to train different FSL models. READ MORE
-
7. Understanding the Robustnessof Self Supervised Representations
University essay from Luleå tekniska universitet/Institutionen för system- och rymdteknikAbstract : This work investigates the robustness of learned representations of self-supervised learn-ing approaches, focusing on distribution shifts in computer vision. Joint embedding architecture and method-based self-supervised learning approaches have shown advancesin learning representations in a label-free manner and efficient knowledge transfer towardreducing human annotation needs. READ MORE
-
8. Evaluating the Viability of Synthetic Pre-training Data for Face Recognition Using a CNN-Based Multiclass Classifier
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Today, face recognition is becoming increasingly accurate and faster with deep learning methods such as convolutional neural networks (CNNs), and is now widely used in areas such as security and entertainment. Typically, these CNNs are trained using real-face datasets like CASIA-WebFace, which was put together using web-crawling of IMDB. READ MORE
-
9. Comparative Analysis of Transformer and CNN Based Models for 2D Brain Tumor Segmentation
University essay from Linköpings universitet/Institutionen för medicinsk teknikAbstract : A brain tumor is an abnormal growth of cells within the brain, which can be categorized into primary and secondary tumor types. The most common type of primary tumors in adults are gliomas, which can be further classified into high-grade gliomas (HGGs) and low-grade gliomas (LGGs). READ MORE
-
10. Sim2Real: Generating synthetic images from industry CAD models with domain randomization
University essay from Uppsala universitet/Institutionen för informationsteknologiAbstract : Deep learning methods for computer vision applications require massive visual data for model training. Although it is possible to utilize public datasets such as ImageNet, MS COCO, and CIFAR-100, it becomes problematic when there is a need for more task-specific data when new training data collection typically is needed. READ MORE
