MT-DSSD: multi-task deconvolutional single shot detector for object detection, segmentation, and grasping detection.
Ryosuke ArakiTsubasa HirakawaTakayoshi YamashitaHironobu FujiyoshiPublished in: Adv. Robotics (2022)
Keyphrases
- object detection
- multi task
- object detectors
- multi task learning
- multi class
- background subtraction
- single shot
- learning tasks
- image segmentation
- face detection
- sparse learning
- computer vision
- object recognition
- multiscale
- learning problems
- bounding box
- vision system
- transfer learning
- light field
- training data
- sparse representation
- image classification
- image analysis
- machine learning