SeMask: Semantically Masked Transformers for Semantic Segmentation.
Jitesh JainAnukriti SinghNikita OrlovZilong HuangJiachen LiSteven WaltonHumphrey ShiPublished in: CoRR (2021)
Keyphrases
- semantic segmentation
- street scenes
- conditional random fields
- superpixels
- label transfer
- weakly supervised
- scene classification
- object categories
- pascal voc
- object classes
- image set
- object class
- image understanding
- object detection
- long range
- multi class
- bag of words
- small number
- probabilistic model
- natural language
- learning algorithm
- image classification
- co occurrence
- object segmentation
- image features
- bounding box
- hidden markov models
- object recognition
- training data
- feature extraction
- image segmentation
- computer vision