Sökning: "Self-Supervision"
Visar resultat 1 - 5 av 10 uppsatser innehållade ordet Self-Supervision.
1. Self-Supervised Learning for Tabular Data: Analysing VIME and introducing Mix Encoder
Kandidat-uppsats, Lunds universitet/Fysiska institutionenSammanfattning : We introduce Mix Encoder, a novel self-supervised learning framework for deep tabular data models based on Mixup [1]. Mix Encoder uses linear interpolations of samples with associated pretext tasks to form useful pre-trained representations. LÄS MER
2. Understanding the Robustnessof Self Supervised Representations
Uppsats för yrkesexamina på avancerad nivå, Luleå tekniska universitet/Institutionen för system- och rymdteknikSammanfattning : 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. LÄS MER
3. Detecting Defective Rail Joints on the Swiss Railways with Inception ResNet V2 : Simplifying Predictive Maintenance of Railway Infrastructure
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Manual investigation of railway infrastructure is a labor-intensive and time-consuming task, and automating it has become a high priority for railway operators to reduce unexpected infrastructure expenditure. In this thesis, we propose a new image classification approach for classifying defect and non-defective rail joints in image data, based on previous fault detection algorithms using object detection. LÄS MER
4. Unsupervised 3D Human Pose Estimation
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The thesis proposes an unsupervised representation learning method to predict 3D human pose from a 2D skeleton via a VAEGAN (Variational Autoencoder Generative Adversarial Network) hybrid network. The method learns to lift poses from 2D to 3D using selfsupervision and adversarial learning techniques. LÄS MER
5. Object Detection and Semantic Segmentation Using Self-Supervised Learning
Master-uppsats, Linköpings universitet/DatorseendeSammanfattning : In this thesis, three well known self-supervised methods have been implemented and trained on road scene images. The three so called pretext tasks RotNet, MoCov2, and DeepCluster were used to train a neural network self-supervised. LÄS MER