MT-DSSD: Deconvolutional Single Shot Detector Using Multi Task Learning for Object Detection, Segmentation, and Grasping Detection.
Ryosuke ArakiTakeshi OnishiTsubasa HirakawaTakayoshi YamashitaHironobu FujiyoshiPublished in: ICRA (2020)
Keyphrases
- object detection
- multi task learning
- multi task
- object detectors
- single shot
- background subtraction
- multiple tasks
- learning tasks
- multi class
- gaussian processes
- face detection
- learning problems
- image segmentation
- computer vision
- transfer learning
- high order
- object categories
- theoretical analysis
- object recognition
- light field
- machine learning
- structured light
- three dimensional
- learning algorithm
- learning models
- edge detection
- active learning