[KSIĄŻKA][B] Synthetic data for deep learning

SI Nikolenko - 2021 - Springer
You are holding in your hands… oh, come on, who holds books like this in their hands
anymore? Anyway, you are reading this, and it means that I have managed to release one of …

Sim-to-real via sim-to-sim: Data-efficient robotic gras** via randomized-to-canonical adaptation networks

S James, P Wohlhart, M Kalakrishnan… - Proceedings of the …, 2019 - openaccess.thecvf.com
Real world data, especially in the domain of robotics, is notoriously costly to collect. One way
to circumvent this can be to leverage the power of simulation to produce large amounts of …

Airsim-w: A simulation environment for wildlife conservation with uavs

E Bondi, D Dey, A Kapoor, J Piavis, S Shah… - Proceedings of the 1st …, 2018 - dl.acm.org
Increases in poaching levels have led to the use of unmanned aerial vehicles (UAVs or
drones) to count animals, locate animals in parks, and even find poachers. Finding poachers …

Easy domain adaptation method for filling the species gap in deep learning-based fruit detection

W Zhang, K Chen, J Wang, Y Shi… - Horticulture Research, 2021 - academic.oup.com
Fruit detection and counting are essential tasks for horticulture research. With computer
vision technology development, fruit detection techniques based on deep learning have …

Self-supervised sim-to-real adaptation for visual robotic manipulation

R Jeong, Y Aytar, D Khosid, Y Zhou… - … on robotics and …, 2020 - ieeexplore.ieee.org
Collecting and automatically obtaining reward signals from real robotic visual data for the
purposes of training reinforcement learning algorithms can be quite challenging and time …