segDeepM: Exploiting segmentation and context in deep neural networks for object detection.
Yukun ZhuRaquel UrtasunRuslan SalakhutdinovSanja FidlerPublished in: CVPR (2015)
Keyphrases
- neural network
- object detection
- object segmentation
- image parsing
- medical images
- computer vision
- contextual information
- pattern recognition
- background subtraction
- fuzzy logic
- segmentation method
- level set
- spatial context
- context aware
- context sensitive
- region growing
- neural network model
- fully automatic
- segmentation accuracy
- object class
- fault diagnosis
- multi class
- object recognition
- image segmentation
- object detection and segmentation
- background modeling
- detecting objects
- scene understanding
- object classification
- medical imaging
- bounding box
- neural nets
- shape prior
- object categories
- image regions
- self organizing maps
- segmentation algorithm
- multiscale
- genetic algorithm