SoftTriple Loss: Deep Metric Learning Without Triplet Sampling.
Qi QianLei ShangBaigui SunJuhua HuTacoma TacomaHao LiRong JinPublished in: ICCV (2019)
Keyphrases
- metric learning
- distance metric
- distance metric learning
- semi supervised
- learning tasks
- machine learning and pattern recognition
- pairwise
- dimensionality reduction
- nearest neighbor classification
- distance function
- mahalanobis metric
- multi task
- kernel matrix
- random sampling
- background knowledge
- feature space
- semi supervised learning
- image processing
- euclidean distance
- pattern recognition
- maximum variance unfolding