Improving the trustworthiness of image classification models by utilizing bounding-box annotations.
Dharma KCChicheng ZhangPublished in: CoRR (2021)
Keyphrases
- bounding box
- classification models
- test images
- input image
- image data
- training data
- multiscale
- image retrieval
- object categories
- region of interest
- image content
- image classification
- target object
- image segmentation
- image features
- keypoints
- image representation
- feature selection
- low level
- similarity measure
- image sequences
- decision trees
- image processing
- high resolution