Reinforcement Learning for Improving Object Detection.
Siddharth NayakBalaraman RavindranPublished in: ECCV Workshops (5) (2020)
Keyphrases
- object detection
- reinforcement learning
- multi class
- pedestrian detection
- function approximation
- scene recognition
- scene understanding
- markov decision processes
- computer vision
- neural network
- state space
- learning algorithm
- machine learning
- temporal difference
- object recognition
- multi agent
- training set
- learning process
- least squares
- object categories
- genetic algorithm
- model free
- reinforcement learning algorithms
- real time