Sökning: "Variationell autoencoder"
Hittade 3 uppsatser innehållade orden Variationell autoencoder.
1. Modulating Depth Map Features to Estimate 3D Human Pose via Multi-Task Variational Autoencoders
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Human pose estimation (HPE) constitutes a fundamental problem within the domain of computer vision, finding applications in diverse fields like motion analysis and human-computer interaction. This paper introduces innovative methodologies aimed at enhancing the accuracy and robustness of 3D joint estimation. LÄS MER
2. Overcoming generative likelihood bias for voxel-based out-of-distribution detection
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Deep learning-based dose prediction is a promising approach to automated radiotherapy planning but carries with it the risk of failing silently when the inputs are highly abnormal compared to the training data. One way to address this issue is to develop a dedicated outlier detector capable of detecting anomalous patient geometries. LÄS MER
3. Fraud Detection on Unlabeled Data with Unsupervised Machine Learning
M1-uppsats, KTH/Hälsoinformatik och logistikSammanfattning : A common problem in systems handling user interaction was the risk for fraudulent behaviour. As an example, in a system with credit card transactions it could have been a person using a another user's account for purchases, or in a system with advertisment it could be bots clicking on ads. LÄS MER