Sökning: "Self-supervised Learning"
Visar resultat 1 - 5 av 49 uppsatser innehållade orden Self-supervised Learning.
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. Exploring adaptation of self-supervised representation learning to histopathology images for liver cancer detection
Uppsats för yrkesexamina på avancerad nivå, Luleå tekniska universitet/Institutionen för system- och rymdteknikSammanfattning : This thesis explores adapting self-supervised representation learning to visual domains beyond natural scenes, focusing on medical imaging. The research addresses the central question: "How can self-supervised representation learning be specifically adapted for detecting liver cancer in histopathology images?" The study utilizes the PAIP 2019 dataset for liver cancer segmentation and employs a self-supervised approach based on the VICReg method. LÄS MER
3. Learning Embeddings for Fashion Images
Master-uppsats, Linköpings universitet/DatorseendeSammanfattning : Today the process of sorting second-hand clothes and textiles is mostly manual. In this master’s thesis, methods for automating this process as well as improving the manual sorting process have been investigated. LÄS MER
4. 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
5. Football Trajectory Modeling Using Masked Autoencoders : Using Masked Autoencoder for Anomaly Detection and Correction for Football Trajectories
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Football trajectory modeling is a powerful tool for predicting and evaluating the movement of a football and its dynamics. Masked autoencoders are scalable self-supervised learners used for representation learning of partially observable data. LÄS MER