12 citations · 15 across the 4 of their papers we have counts for
4 papers
Whitening Consistently Improves Self-Supervised Learning
András Kalapos, Bálint Gyires-Tóth
Self-supervised learning (SSL) has been shown to be a powerful approach for learning visual representations. In this study, we propose incorporating ZCA whitening as the final laye…
CNN-JEPA: Self-Supervised Pretraining Convolutional Neural Networks Using Joint Embedding Predictive Architecture
András Kalapos, Bálint Gyires-Tóth
Self-supervised learning (SSL) has become an important approach in pretraining large neural networks, enabling unprecedented scaling of model and dataset sizes. While recent advanc…
Self-Supervised Pretraining for 2D Medical Image Segmentation
András Kalapos, Bálint Gyires-Tóth
Supervised machine learning provides state-of-the-art solutions to a wide range of computer vision problems. However, the need for copious labelled training data limits the capabil…
Sim-to-real reinforcement learning applied to end-to-end vehicle control
András Kalapos, Csaba Gór, Róbert Moni +1
In this work, we study vision-based end-to-end reinforcement learning on vehicle control problems, such as lane following and collision avoidance. Our controller policy is able to…