1 code implementation • 29 May 2024 • Niclas Vödisch, Kürsat Petek, Markus Käppeler, Abhinav Valada, Wolfram Burgard
A key challenge for the widespread application of learning-based models for robotic perception is to significantly reduce the required amount of annotated training data while achieving accurate predictions.
1 code implementation • 19 Sep 2023 • Markus Käppeler, Kürsat Petek, Niclas Vödisch, Wolfram Burgard, Abhinav Valada
Concurrently, recent breakthroughs in visual representation learning have sparked a paradigm shift leading to the advent of large foundation models that can be trained with completely unlabeled images.