End-to-end metric learning from corrupted images using triplet dimensionality reduction loss.
JuHyeon ParkJin HongJunseok KwonPublished in: Expert Syst. Appl. (2024)
Keyphrases
- end to end
- metric learning
- dimensionality reduction
- image data
- principal components
- distance metric
- text localization and recognition
- distance metric learning
- congestion control
- multi task
- semi supervised
- image classification
- high dimensional data
- high dimensional
- learning tasks
- feature selection
- principal component analysis
- data sets
- image set
- pattern recognition
- decision trees
- mahalanobis metric
- distance function
- euclidean distance
- image features
- feature vectors
- image annotation
- similarity measure
- computer vision