Squeeze-SegNet: A new fast Deep Convolutional Neural Network for Semantic Segmentation.
Géraldin NanfackAzeddine ElhassounyRachid Oulad Haj ThamiPublished in: CoRR (2017)
Keyphrases
- semantic segmentation
- convolutional neural network
- street scenes
- face detection
- conditional random fields
- superpixels
- label transfer
- scene classification
- weakly supervised
- pascal voc
- object categories
- object detection
- object classes
- object class
- image understanding
- image set
- neural network
- segmentation algorithm
- pairwise
- biologically inspired
- detection method
- pixel level
- graphical models
- input image
- image features
- probabilistic model
- object recognition
- multiscale