Signal-To-Noise Ratio: A Robust Distance Metric for Deep Metric Learning.
Tongtong YuanWeihong DengJian TangYinan TangBinghui ChenPublished in: CVPR (2019)
Keyphrases
- distance metric
- metric learning
- signal to noise ratio
- distance metric learning
- euclidean distance
- distance function
- distance measure
- edge detection
- linear transformation
- mahalanobis distance
- mahalanobis metric
- nearest neighbor classification
- dimensionality reduction
- semi supervised
- learning tasks
- data points
- kernel matrix
- multi task
- pairwise constraints
- kernel learning
- pairwise
- feature space
- image processing
- learned metric
- similarity search
- decision trees
- e learning