Transfer Sampling with Optimal Transport and window cropping finds nearly 80% of animals in new UAV datasets using under 0.5% of labels.
Deep learning,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2019 2verdicts
UNVERDICTED 2representative citing papers
VRLS is a single reinforcement learning formulation for V2V resource scheduling that works across different densities and channel conditions, reduces collisions and half-duplex errors relative to prior schedulers, and supports transfer with limited retraining.
citing papers explorer
-
Half a Percent of Labels is Enough: Efficient Animal Detection in UAV Imagery using Deep CNNs and Active Learning
Transfer Sampling with Optimal Transport and window cropping finds nearly 80% of animals in new UAV datasets using under 0.5% of labels.
-
VRLS: A Unified Reinforcement Learning Scheduler for Vehicle-to-Vehicle Communications
VRLS is a single reinforcement learning formulation for V2V resource scheduling that works across different densities and channel conditions, reduces collisions and half-duplex errors relative to prior schedulers, and supports transfer with limited retraining.