SemAug: Semantically Meaningful Image Augmentations for Object Detection Through Language Grounding.
Morgan HeislerAmin Banitalebi-DehkordiYong ZhangPublished in: ECCV (36) (2022)
Keyphrases
- semantically meaningful
- object detection
- object level
- image classification
- image data
- image features
- single image
- visual patterns
- image representation
- input image
- template matching
- high resolution
- image retrieval
- multiscale
- image segmentation
- pixel level
- test images
- segmentation method
- higher level
- image processing
- low level